Journal articles on the topic 'Fine-grained image analysi'
To see the other types of publications on this topic, follow the link: Fine-grained image analysi.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Fine-grained image analysi.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Lv, Zhihan, Liang Qiao, Amit Kumar Singh, and Qingjun Wang. "Fine-Grained Visual Computing Based on Deep Learning." ACM Transactions on Multimedia Computing, Communications, and Applications 17, no. 1s (April 20, 2021): 1–19. http://dx.doi.org/10.1145/3418215.
Full textAbstract:
With increasing amounts of information, the image information received by people also increases exponentially. To perform fine-grained categorization and recognition of images and visual calculations, this study combines the Visual Geometry Group Network 16 model of convolutional neural networks and the vision attention mechanism to build a multi-level fine-grained image feature categorization model. Finally, the TensorFlow platform is utilized to simulate the fine-grained image classification model based on the visual attention mechanism. The results show that in terms of accuracy and required training time, the fine-grained image categorization effect of the multi-level feature categorization model constructed by this study is optimal, with an accuracy rate of 85.3% and a minimum training time of 108 s. In the similarity effect analysis, it is found that the chi-square distance between Log Gabor features and the degree of image distortion show a strong positive correlation; in addition, the validity of this measure is verified. Therefore, through the research in this study, it is found that the constructed fine-grained image categorization model has higher accuracy in image recognition categorization, shorter training time, and significantly better performance in similar feature effects, which provides an experimental reference for the visual computing of fine-grained images in the future.
2
Zhou, Dehui. "Image Recognition of Pledges of Capital Stock in Small- and Medium-Sized Enterprises Based on Partial Differential Equations." Advances in Mathematical Physics 2021 (November 1, 2021): 1–10. http://dx.doi.org/10.1155/2021/6548344.
Full textAbstract:
Image recognition is one of the core research directions in the field of computer vision research, which can be divided into general image recognition and fine-grained image recognition. General image recognition refers to the recognition of different types of objects; fine-grained image recognition refers to the recognition of different subclasses in the same broad class of objects, such as SME financing inventory pledge image recognition. In this paper, we propose a partial differential equation-based image recognition method for SME financing inventory pledges and conduct detailed analysis and experiments. Compared with general images, partial differential equation-based SME financing inventory pledges image recognition is difficult to recognize due to data characteristics such as small differences in features between classes, large differences in features within classes, and a small percentage of targets in the image. To address the problem that existing methods ignore the role of shallow features on fine-grained image recognition, this paper proposes a fine-grained image recognition method based on partial differential equations. By analyzing the important role of shallow features for fine-grained image recognition, a feature fusion method with adaptive weights is proposed. Using this method to fuse shallow and high-level semantic features for recognition, the role of shallow features in fine-grained image recognition is fully exploited. In addition, the proposed method does not change the order of magnitude of the model parameters and is highly transferable. The relevant experimental results verify the effectiveness of the proposed method.
3
Sun, Yingxue, and Junbo Gao. "Fine-grained Multimodal Sentiment Analysis Based on Gating and Attention Mechanism." Electronics Science Technology and Application 7, no. 4 (January 21, 2021): 123. http://dx.doi.org/10.18686/esta.v7i4.166.
Full textAbstract:
<p>In recent years, more and more people express their feelings through both images and texts, boosting the growth of multimodal data. Multimodal data contains richer semantics and is more conducive to judging the real emotions of people. To fully learn the features of every single modality and integrate modal information, this paper proposes a fine-grained multimodal sentiment analysis method FCLAG based on gating and attention mechanism. First, the method is carried out from the character level and the word level in the text aspect. CNN is used to extract more fine-grained emotional information from characters, and the attention mechanism is used to improve the expressiveness of the keywords. In terms of images, a gating mechanism is added to control the flow of image information between networks. The images and text vectors represent the original data collectively. Then the bidirectional LSTM is used to complete further learning, which enhances the information interaction capability between the modalities. Finally, put the multimodal feature expression into the classifier. This method is verified on a self-built image and text dataset. The experimental results show that compared with other sentiment classification models, this method has greater improvement in accuracy and F1 score and it can effectively improve the performance of multimodal sentiment analysis.</p>
4
Wang, Xiaoqin, Rushi Lan, Huadeng Wang, Zhenbing Liu, and Xiaonan Luo. "Fine-grained correlation analysis for medical image retrieval." Computers & Electrical Engineering 90 (March 2021): 106992. http://dx.doi.org/10.1016/j.compeleceng.2021.106992.
Full text
5
Yan, Yichao, Bingbing Ni, Huawei Wei, and Xiaokang Yang. "Fine-grained image analysis via progressive feature learning." Neurocomputing 396 (July 2020): 254–65. http://dx.doi.org/10.1016/j.neucom.2018.07.100.
Full text
6
Guo, Jinyi, Wei Ren, Yi Ren, and Tianqin Zhu. "A Watermark-Based in-Situ Access Control Model for Image Big Data." Future Internet 10, no. 8 (July 29, 2018): 69. http://dx.doi.org/10.3390/fi10080069.
Full textAbstract:
When large images are used for big data analysis, they impose new challenges in protecting image privacy. For example, a geographic image may consist of several sensitive areas or layers. When it is uploaded into servers, the image will be accessed by diverse subjects. Traditional access control methods regulate access privileges to a single image, and their access control strategies are stored in servers, which imposes two shortcomings: (1) fine-grained access control is not guaranteed for areas/layers in a single image that need to maintain secret for different roles; and (2) access control policies that are stored in servers suffers from multiple attacks (e.g., transferring attacks). In this paper, we propose a novel watermark-based access control model in which access control policies are associated with objects being accessed (called an in-situ model). The proposed model integrates access control policies as watermarks within images, without relying on the availability of servers or connecting networks. The access control for images is still maintained even though images are redistributed again to further subjects. Therefore, access control policies can be delivered together with the big data of images. Moreover, we propose a hierarchical key-role-area model for fine-grained encryption, especially for large size images such as geographic maps. The extensive analysis justifies the security and performance of the proposed model
7
Kothari, Kushal, Ajay Arjunwadkar, Hitesh Bhalerao, and Savita Lade. "Fine-Grained Identification of Clothing Apparels." International Journal for Research in Applied Science and Engineering Technology 10, no. 4 (April 30, 2022): 3168–71. http://dx.doi.org/10.22214/ijraset.2022.42022.
Full textAbstract:
Abstract: The rapid use of smartphones and tablet computers, search is now not just limited to text,but moved to other modalities such as voice and image. Extracting and matching this attributes still remains a daunting task due to high deformability and variability of clothing items. Visual analysis of clothings is a topic that has received attention due to tremendous growth of e-commerce fashion stores. Analyzing fashion attributes is also crucial in the fashion design process. This paper addresses the solution of recognition of clothes and fashion related attributes related to it using better image segmentation RCNN based algorithms. Keywords: Computer Vision, Fine grained identification, Clothing apparel detection, Convolutional Neural Network, Mask RCNN, Detectron2
8
Ma, Kai, Ming-Jun Nie, Sen Lin, Jianlei Kong, Cheng-Cai Yang, and Jinhao Liu. "Fine-Grained Pests Recognition Based on Truncated Probability Fusion Network via Internet of Things in Forestry and Agricultural Scenes." Algorithms 14, no. 10 (September 30, 2021): 290. http://dx.doi.org/10.3390/a14100290.
Full textAbstract:
Accurate identification of insect pests is the key to improve crop yield and ensure quality and safety. However, under the influence of environmental conditions, the same kind of pests show obvious differences in intraclass representation, while the different kinds of pests show slight similarities. The traditional methods have been difficult to deal with fine-grained identification of pests, and their practical deployment is low. In order to solve this problem, this paper uses a variety of equipment terminals in the agricultural Internet of Things to obtain a large number of pest images and proposes a fine-grained identification model of pests based on probability fusion network FPNT. This model designs a fine-grained feature extractor based on an optimized CSPNet backbone network, mining different levels of local feature expression that can distinguish subtle differences. After the integration of the NetVLAD aggregation layer, the gated probability fusion layer gives full play to the advantages of information complementarity and confidence coupling of multi-model fusion. The comparison test shows that the PFNT model has an average recognition accuracy of 93.18% for all kinds of pests, and its performance is better than other deep-learning methods, with the average processing time drop to 61 ms, which can meet the needs of fine-grained image recognition of pests in the Internet of Things in agricultural and forestry practice, and provide technical application reference for intelligent early warning and prevention of pests.
9
Liu, Haipeng, Jiangtao Wang, Yayuan Geng, Kunwei Li, Han Wu, Jian Chen, Xiangfei Chai, Shaolin Li, and Dingchang Zheng. "Fine-Grained Assessment of COVID-19 Severity Based on Clinico-Radiological Data Using Machine Learning." International Journal of Environmental Research and Public Health 19, no. 17 (August 26, 2022): 10665. http://dx.doi.org/10.3390/ijerph191710665.
Full textAbstract:
Background: The severe and critical cases of COVID-19 had high mortality rates. Clinical features, laboratory data, and radiological features provided important references for the assessment of COVID-19 severity. The machine learning analysis of clinico-radiological features, especially the quantitative computed tomography (CT) image analysis results, may achieve early, accurate, and fine-grained assessment of COVID-19 severity, which is an urgent clinical need. Objective: To evaluate if machine learning algorithms using CT-based clinico-radiological features could achieve the accurate fine-grained assessment of COVID-19 severity. Methods: The clinico-radiological features were collected from 78 COVID-19 patients with different severities. A neural network was developed to automatically measure the lesion volume from CT images. The severity was clinically diagnosed using two-type (severe and non-severe) and fine-grained four-type (mild, regular, severe, critical) classifications, respectively. To investigate the key features of COVID-19 severity, statistical analyses were performed between patients’ clinico-radiological features and severity. Four machine learning algorithms (decision tree, random forest, SVM, and XGBoost) were trained and applied in the assessment of COVID-19 severity using clinico-radiological features. Results: The CT imaging features (CTscore and lesion volume) were significantly related with COVID-19 severity (p < 0.05 in statistical analysis for both in two-type and fine-grained four-type classifications). The CT imaging features significantly improved the accuracy of machine learning algorithms in assessing COVID-19 severity in the fine-grained four-type classification. With CT analysis results added, the four-type classification achieved comparable performance to the two-type one. Conclusions: CT-based clinico-radiological features can provide an important reference for the accurate fine-grained assessment of illness severity using machine learning to achieve the early triage of COVID-19 patients.
10
Hirota, Katsuya, Tomoko Ariga, Masahiro Hino, Go Ichikawa, Shinsuke Kawasaki, Masaaki Kitaguchi, Kenji Mishima, Naoto Muto, Naotaka Naganawa, and Hirohiko M. Shimizu. "Neutron Imaging Using a Fine-Grained Nuclear Emulsion." Journal of Imaging 7, no. 1 (January 5, 2021): 4. http://dx.doi.org/10.3390/jimaging7010004.
Full textAbstract:
A neutron detector using a fine-grained nuclear emulsion has a sub-micron spatial resolution and thus has potential to be applied as high-resolution neutron imaging. In this paper, we present two approaches to applying the emulsion detectors for neutron imaging. One is using a track analysis to derive the reaction points for high resolution. From an image obtained with a 9 μm pitch Gd grating with cold neutrons, periodic peak with a standard deviation of 1.3 μm was observed. The other is an approach without a track analysis for high-density irradiation. An internal structure of a crystal oscillator chip, with a scale of approximately 30 μm, was able to be observed after an image analysis.
11
Ferrara, Pasquale, Tiziano Bianchi, Alessia De Rosa, and Alessandro Piva. "Image Forgery Localization via Fine-Grained Analysis of CFA Artifacts." IEEE Transactions on Information Forensics and Security 7, no. 5 (October 2012): 1566–77. http://dx.doi.org/10.1109/tifs.2012.2202227.
Full text
12
Wang, Lei. "Cartoon-Style Image Rendering Transfer Based on Neural Networks." Computational Intelligence and Neuroscience 2022 (July 16, 2022): 1–10. http://dx.doi.org/10.1155/2022/2958338.
Full textAbstract:
Cartoon rendering of images is a challenging nonphotorealistic image rendering task, which aims to transform real photos into cartoon-style nonphotorealistic images while preserving the semantic content and texture details of the original photos. Based on the understanding of the characteristics of cartoon images and analysis of the defects of established approaches, this paper improves existing methods. The convolutional neural networks’ powerful image processing ability and attention mechanism are utilized to get more fine-grained image features, making the result of rendering more realistic. This paper mainly studies how neural networks can better process cartoon pictures, adjust parameters, and choose training methods. Furthermore, the article proposes a new solution of cartoon-style image rendering based on deep learning. The actual test results of real original images have shown that the model is suitable for cartoon-style image rendering.
13
C. Burkapalli, Vishwanath, and Priyadarshini C. Patil. "Food image segmentation using edge adaptive based deep-CNNs." International Journal of Intelligent Unmanned Systems 8, no. 4 (December 23, 2019): 243–52. http://dx.doi.org/10.1108/ijius-09-2019-0053.
Full textAbstract:
Purpose Indian food recognition can be considered as a case of fine-grained type visual recognition, where the several photos of same category generally have significant variability. Therefore, effective segmentation and classification technique is required to identify the particular cuisines and fine-grained analysis. The paper aims to discuss this issue. Design/methodology/approach In this paper, the authors provided an effective segmentation approach through the proposed edge adaptive (EA)-deep convolutional neural networks (DCNNs) model, where each input images are divided into patches in order to provide much efficient and accurate structural description of data. Findings EA-DCNNs starts with developing a coarse map of feature that obtained through DCNN, afterwards EA model is applied to construct the final segmented image. Originality/value The training model of EA-DCNN consists of pooling, rectified linear unit and convolution, which help convolutional network to optimize the performance of segmentation in a significant extent, which is much practical and relevant in the context of food image segmentation.
14
Muneem, Abdul, Junya Yoshida, Hiroyuki Ekawa, Masahiro Hino, Katsuya Hirota, Go Ichikawa, Ayumi Kasagi, et al. "Investigation of neutron imaging applications using fine-grained nuclear emulsion." Journal of Applied Physics 133, no. 5 (February 7, 2023): 054902. http://dx.doi.org/10.1063/5.0131098.
Full textAbstract:
Neutron imaging is a nondestructive inspection technique that has a wide range of applications. One of the important aspects of neutron imaging is achieving a micrometer-scale spatial resolution. The development of a high-resolution neutron detector is a challenging task. As one potential solution to this task, we investigate whether neutron detectors based on fine-grained nuclear emulsions are suitable for high-resolution neutron imaging applications. High track density is necessary to improve the quality of neutron imaging. However, the available track analysis methods are difficult to apply under high track density conditions. Simulated images are used to determine the required track density for neutron imaging. A track density of the order of [Formula: see text] tracks per [Formula: see text] is sufficient to utilize neutron detectors for imaging applications. Contrast resolution was also investigated for image datasets with various track densities and neutron transmission rates. Moreover, experiments were performed for the neutron imaging of gadolinium-based gratings with known geometries. The grating structures were successfully resolved. The calculated [Formula: see text] 10%–90% edge response using the grayscale optical images of the grating slit with a periodic structure of 9 [Formula: see text]m was [Formula: see text] [Formula: see text]m.
15
Chemock, Richard S. "Application of an image management system in microscopy." Proceedings, annual meeting, Electron Microscopy Society of America 50, no. 2 (August 1992): 1052–53. http://dx.doi.org/10.1017/s0424820100129899.
Full textAbstract:
One of the most common tasks in a typical analysis lab is the recording of images. Many analytical techniques (TEM, SEM, and metallography for example) produce images as their primary output. Until recently, the most common method of recording images was by using film. Current PS/2R systems offer very large capacity data storage devices and high resolution displays, making it practical to work with analytical images on PS/2s, thereby sidestepping the traditional film and darkroom steps. This change in operational mode offers many benefits: cost savings, throughput, archiving and searching capabilities as well as direct incorporation of the image data into reports.The conventional way to record images involves film, either sheet film (with its associated wet chemistry) for TEM or PolaroidR film for SEM and light microscopy. Although film is inconvenient, it does have the highest quality of all available image recording techniques. The fine grained film used for TEM has a resolution that would exceed a 4096x4096x16 bit digital image.
16
Wang, Shijie, Haojie Li, Zhihui Wang, and Wanli Ouyang. "Dynamic Position-aware Network for Fine-grained Image Recognition." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 4 (May 18, 2021): 2791–99. http://dx.doi.org/10.1609/aaai.v35i4.16384.
Full textAbstract:
Most weakly supervised fine-grained image recognition (WFGIR) approaches predominantly focus on learning the discriminative details which contain the visual variances and position clues. The position clues can be indirectly learnt by utilizing context information of discriminative visual content. However, this will cause the selected discriminative regions containing some non-discriminative information introduced by the position clues. These analysis motivate us to directly introduce position clues into visual content to only focus on the visual variances, achieving more precise discriminative region localization. Though important, position modelling usually requires significant pixel/region annotations and therefore is labor-intensive. To address this issue, we propose an end-to-end Dynamic Position-aware Network (DP-Net) to directly incorporate the position clues into visual content and dynamically align them without extra annotations, which eliminates the effect of position information for visual variances of subcategories. In particular, the DP-Net consists of: 1) Position Encoding Module, which learns a set of position-aware parts by directly adding the learnable position information into the horizontal/vertical visual content of images; 2) Position-vision Aligning Module, which dynamically aligns both visual content and learnable position information via performing graph convolution on position-aware parts; 3) Position-vision Reorganization Module, which projects the aligned position clues and visual content into the Euclidean space to construct a position-aware feature maps. Finally, the position-aware feature maps are used which is implicitly applied the aligned visual content and position clues for more accurate discriminative regions localization. Extensive experiments verify that DP-Net yields the best performance under the same settings with most competitive approaches, on CUB Bird, Stanford-Cars, and FGVC Aircraft datasets.
17
Ibrahim, Hussein A. H., John R. Kender, and David Elliot Shaw. "Low-level image analysis tasks on fine-grained tree-structured SIMD machines." Journal of Parallel and Distributed Computing 4, no. 6 (December 1987): 546–74. http://dx.doi.org/10.1016/0743-7315(87)90030-x.
Full text
18
Kuchařová, Aneta, Jens Götze, Šárka Šachlová, Zdeněk Pertold, and Richard Přikryl. "Microscopy and Cathodoluminescence Spectroscopy Characterization of Quartz Exhibiting Different Alkali–Silica Reaction Potential." Microscopy and Microanalysis 22, no. 1 (January 21, 2016): 189–98. http://dx.doi.org/10.1017/s1431927615015524.
Full textAbstract:
AbstractDifferent quartz types from several localities in the Czech Republic and Sweden were examined by polarizing microscopy combined with cathodoluminescence (CL) microscopy, spectroscopy, and petrographic image analysis, and tested by use of an accelerated mortar bar test (following ASTM C1260). The highest alkali–silica reaction potential was indicated by very fine-grained chert, containing significant amounts of fine-grained to cryptocrystalline matrix. The chert exhibited a dark red CL emission band at ~640 nm with a low intensity. Fine-grained orthoquartzites, as well as fine-grained metamorphic vein quartz, separated from phyllite exhibited medium expansion values. The orthoquartzites showed various CL of quartz grains, from blue through violet, red, and brown. Two CL spectral bands at ~450 and ~630 nm, with various intensities, were detected. The quartz from phyllite displayed an inhomogeneous dark red CL with two CL spectral bands of low intensities at ~460 and ~640 nm. The massive coarse-grained pegmatite quartz from pegmatite was assessed to be nonreactive and displayed a typical short-lived blue CL (~480 nm). The higher reactivity of the fine-grained hydrothermal quartz may be connected with high concentrations of defect centers, and probably with amorphized micro-regions in the quartz, respectively; indicated by a yellow CL emission (~570 nm).
19
Cucchiara, Rita, and Matteo Fabbri. "Fine-grained Human Analysis under Occlusions and Perspective Constraints in Multimedia Surveillance." ACM Transactions on Multimedia Computing, Communications, and Applications 18, no. 1s (February 28, 2022): 1–23. http://dx.doi.org/10.1145/3476839.
Full textAbstract:
Human detection in the wild is a research topic of paramount importance in computer vision, and it is the starting step for designing intelligent systems oriented to human interaction that work in complete autonomy. To achieve this goal, computer vision and machine learning should aim at superhuman capabilities. In this work, we address the problem of fine-grained human analysis under occlusions and perspective constraints. More specifically, we discuss some issues and some possible solutions to effectively detect people using pose estimation methods and to detect humans under occlusions both in the two-dimensional (2D) image plane and in the 3D space exploiting single monocular cameras. Dealing with occlusion can be done at the joint level or pixel level: We discuss two different solutions, the former based on a supervised neural network architecture for detecting occluded joints and the latter based on a semi-supervised specialized GAN that exploits both appearance and human shape attributes to determine the missing parts of the visible shape. To deal with perspective constraints, we further discuss a neural approach based on a double architecture that learns to create an optimal neural representation, which is useful to reconstruct the 3D position of human keypoints starting with simple RGB images. All these approaches have a critical point in common: the need for large annotated datasets. To have large, fair, consistent, transparent, and ethical datasets, we propose the adoption of synthetic datasets as, for example, JTA and MOTSynth. In this article, we discuss the pros and cons of using synthetic datasets while tackling several human-centered AI issues with respect to European GDPR rules for privacy. We further explore and discuss an application in the field of risk assessment by space occupancy estimation during the COVID-19 pandemic called Inter-Homines.
20
Kong, Jianlei, Chengcai Yang, Yang Xiao, Sen Lin, Kai Ma, and Qingzhen Zhu. "A Graph-Related High-Order Neural Network Architecture via Feature Aggregation Enhancement for Identification Application of Diseases and Pests." Computational Intelligence and Neuroscience 2022 (May 26, 2022): 1–16. http://dx.doi.org/10.1155/2022/4391491.
Full textAbstract:
Diseases and pests are essential threat factors that affect agricultural production, food security supply, and ecological plant diversity. However, the accurate recognition of various diseases and pests is still challenging for existing advanced information and intelligence technologies. Disease and pest recognition is typically a fine-grained visual classification problem, which is easy to confuse the traditional coarse-grained methods due to the external similarity between different categories and the significant differences among each subsample of the same category. Toward this end, this paper proposes an effective graph-related high-order network with feature aggregation enhancement (GHA-Net) to handle the fine-grained image recognition of plant pests and diseases. In our approach, an improved CSP-stage backbone network is first formed to offer massive channel-shuffled features in multiple granularities. Secondly, relying on the multilevel attention mechanism, the feature aggregation enhancement module is designed to exploit distinguishable fine-grained features representing different discriminating parts. Meanwhile, the graphic convolution module is constructed to analyse the graph-correlated representation of part-specific interrelationships by regularizing semantic features into the high-order tensor space. With the collaborative learning of three modules, our approach can grasp the robust contextual details of diseases and pests for better fine-grained identification. Extensive experiments on several public fine-grained disease and pest datasets demonstrate that the proposed GHA-Net achieves better performances in accuracy and efficiency surpassing several other existing models and is more suitable for fine-grained identification applications in complex scenes.
21
Qin, RuoXi, Zhenzhen Wang, LingYun Jiang, Kai Qiao, Jinjin Hai, Jian Chen, Junling Xu, Dapeng Shi, and Bin Yan. "Fine-Grained Lung Cancer Classification from PET and CT Images Based on Multidimensional Attention Mechanism." Complexity 2020 (January 20, 2020): 1–12. http://dx.doi.org/10.1155/2020/6153657.
Full textAbstract:
Lung cancer ranks among the most common types of cancer. Noninvasive computer-aided diagnosis can enable large-scale rapid screening of potential patients with lung cancer. Deep learning methods have already been applied for the automatic diagnosis of lung cancer in the past. Due to restrictions caused by single modality images of dataset as well as the lack of approaches that allow for a reliable extraction of fine-grained features from different imaging modalities, research regarding the automated diagnosis of lung cancer based on noninvasive clinical images requires further study. In this paper, we present a deep learning architecture that combines the fine-grained feature from PET and CT images that allow for the noninvasive diagnosis of lung cancer. The multidimensional (regarding the channel as well as spatial dimensions) attention mechanism is used to effectively reduce feature noise when extracting fine-grained features from each imaging modality. We conduct a comparative analysis of the two aspects of feature fusion and attention mechanism through quantitative evaluation metrics and the visualization of deep learning process. In our experiments, we obtained an area under the ROC curve of 0.92 (balanced accuracy = 0.72) and a more focused network attention which shows the effective extraction of the fine-grained feature from each imaging modality.
22
Zhang, Xiuwei, Yang Zhou, Jiaojiao Jin, Yafei Wang, Minhao Fan, Ning Wang, and Yanning Zhang. "ICENETv2: A Fine-Grained River Ice Semantic Segmentation Network Based on UAV Images." Remote Sensing 13, no. 4 (February 10, 2021): 633. http://dx.doi.org/10.3390/rs13040633.
Full textAbstract:
Accurate ice segmentation is one of the most crucial techniques for intelligent ice monitoring. Compared with ice segmentation, it can provide more information for ice situation analysis, change trend prediction, and so on. Therefore, the study of ice segmentation has important practical significance. In this study, we focused on fine-grained river ice segmentation using unmanned aerial vehicle (UAV) images. This has the following difficulties: (1) The scale of river ice varies greatly in different images and even in the same image; (2) the same kind of river ice differs greatly in color, shape, texture, size, and so on; and (3) the appearances of different kinds of river ice sometimes appear similar due to the complex formation and change procedure. Therefore, to perform this study, the NWPU_YRCC2 dataset was built, in which all UAV images were collected in the Ningxia–Inner Mongolia reach of the Yellow River. Then, a novel semantic segmentation method based on deep convolution neural network, named ICENETv2, is proposed. To achieve multiscale accurate prediction, we design a multilevel features fusion framework, in which multi-scale high-level semantic features and lower-level finer features are effectively fused. Additionally, a dual attention module is adopted to highlight distinguishable characteristics, and a learnable up-sampling strategy is further used to improve the segmentation accuracy of the details. Experiments show that ICENETv2 achieves the state-of-the-art on the NWPU_YRCC2 dataset. Finally, our ICENETv2 is also applied to solve a realistic problem, calculating drift ice cover density, which is one of the most important factors to predict the freeze-up data of the river. The results demonstrate that the performance of ICENETv2 meets the actual application demand.
23
Lin, Zhouchen, Junfeng He, Xiaoou Tang, and Chi-Keung Tang. "Fast, automatic and fine-grained tampered JPEG image detection via DCT coefficient analysis." Pattern Recognition 42, no. 11 (November 2009): 2492–501. http://dx.doi.org/10.1016/j.patcog.2009.03.019.
Full text
24
Hong, Xianbin, Sheng-Uei Guan, Nian Xue, Zhen Li, Ka Lok Man, Prudence W. H. Wong, and Dawei Liu. "Dual-Track Lifelong Machine Learning-Based Fine-Grained Product Quality Analysis." Applied Sciences 13, no. 3 (January 17, 2023): 1241. http://dx.doi.org/10.3390/app13031241.
Full textAbstract:
Artificial intelligence (AI) systems are becoming wiser, even surpassing human performances in some fields, such as image classification, chess, and Go. However, most high-performance AI systems, such as deep learning models, are black boxes (i.e., only system inputs and outputs are visible, but the internal mechanisms are unknown) and, thus, are notably challenging to understand. Thereby a system with better explainability is needed to help humans understand AI. This paper proposes a dual-track AI approach that uses reinforcement learning to supplement fine-grained deep learning-based sentiment classification. Through lifelong machine learning, the dual-track approach can gradually become wiser and realize high performance (while keeping outstanding explainability). The extensive experimental results show that the proposed dual-track approach can provide reasonable fine-grained sentiment analyses to product reviews and remarkably achieve a 133% promotion of the Macro-F1 score on the Twitter sentiment classification task and a 27.12% promotion of the Macro-F1 score on an Amazon iPhone 11 sentiment classification task, respectively.
25
Park, Myeong-heom, Akinobu Shibata, and Nobuhiro Tsuji. "Effect of Grain Size on Mechanical Properties of Dual Phase Steels Composed of Ferrite and Martensite." MRS Advances 1, no. 12 (2016): 811–16. http://dx.doi.org/10.1557/adv.2016.230.
Full textAbstract:
ABSTRACTIt is well-known that dual phase (DP) steels composed of ferrite and martensite have good ductility and plasticity as well as high strength. Due to their excellent mechanical properties, DP steels are widely used in the industrial field. The mechanical properties of DP steels strongly depend on several factors such as fraction, distribution and grain size of each phase. In this study, the grain size effect on mechanical properties of DP steels was investigated. In order to obtain DP structures with different grain sizes, intercritical heat treatment in ferrite + austenite two-phase region was carried out for ferrite-pearlite structures having coarse and fine ferrite grain sizes. These ferrite-pearlite structures with coarse and fine grains were fabricated by two types of heat treatments; austenitizing heat treatment and repetitive heat treatment. Ferrite grain sizes of the specimens heat-treated by austenitizing and repetitive heat treatment were 47.5 µm (coarse grain) and 4.5 µm (fine grain), respectively. The ferrite grain sizes in the final DP structures fabricated from the coarse-grained and fine-grained ferrite-pearlite structures were 58.3 µm and 4.1µm, respectively. The mechanical behavior of the DP structures with different grain sizes was evaluated by an uniaxial tensile test at room temperature. The local strain distribution in the specimens during tensile test was obtained by a digital image correlation (DIC) technique. Results of the tensile test showed that the fine-grained DP structure had higher strength and larger elongation than the coarse-grained DP structure. It was found by the DIC analysis that the fine-grained DP structure showed homogeneous deformation compared with the coarse-grained DP structure.
26
Xu, Xing, Yifan Wang, Yixuan He, Yang Yang, Alan Hanjalic, and Heng Tao Shen. "Cross-Modal Hybrid Feature Fusion for Image-Sentence Matching." ACM Transactions on Multimedia Computing, Communications, and Applications 17, no. 4 (November 30, 2021): 1–23. http://dx.doi.org/10.1145/3458281.
Full textAbstract:
Image-sentence matching is a challenging task in the field of language and vision, which aims at measuring the similarities between images and sentence descriptions. Most existing methods independently map the global features of images and sentences into a common space to calculate the image-sentence similarity. However, the image-sentence similarity obtained by these methods may be coarse as (1) an intermediate common space is introduced to implicitly match the heterogeneous features of images and sentences in a global level, and (2) only the inter-modality relations of images and sentences are captured while the intra-modality relations are ignored. To overcome the limitations, we propose a novel Cross-Modal Hybrid Feature Fusion (CMHF) framework for directly learning the image-sentence similarity by fusing multimodal features with inter- and intra-modality relations incorporated. It can robustly capture the high-level interactions between visual regions in images and words in sentences, where flexible attention mechanisms are utilized to generate effective attention flows within and across the modalities of images and sentences. A structured objective with ranking loss constraint is formed in CMHF to learn the image-sentence similarity based on the fused fine-grained features of different modalities bypassing the usage of intermediate common space. Extensive experiments and comprehensive analysis performed on two widely used datasets—Microsoft COCO and Flickr30K—show the effectiveness of the hybrid feature fusion framework in CMHF, in which the state-of-the-art matching performance is achieved by our proposed CMHF method.
27
Yang, Jiachen, Yue Yang, Yang Li, Shuai Xiao, and Sezai Ercisli. "Image Information Contribution Evaluation for Plant Diseases Classification via Inter-Class Similarity." Sustainability 14, no. 17 (September 1, 2022): 10938. http://dx.doi.org/10.3390/su141710938.
Full textAbstract:
Combineingplant diseases identification and deep learning algorithm can achieve cost-effective prevention effect, and has been widely used. However, the current field of intelligent plant diseases identification still faces the problems of insufficient data and inaccurate classification. Aiming to resolve these problems, the present research proposes an image information contribution evaluation method based on the analysis of inter-class similarity. Combining this method with the active learning image selection strategy can provide guidance for the collection and annotation of intelligent identification datasets of plant diseases, so as to improve the recognition effect and reduce the cost. The method proposed includes two modules: the inter-classes similarity evaluation module and the image information contribution evaluation module. The images located on the decision boundary between high similarity classes will be analysis as high information contribution images, they will provide more information for plant diseases classification. In order to verify the effectiveness of this method, experiments were carried on the fine-grained classification dataset of tomato diseases. Experimental results confirm the superiority of this method compared with others. This research is in the field of plant disease classification. For the detection and segmentation, further research is advisable.
28
Matuszek, Dominika Barbara, and Łukasz Andrzej Biłos. "Computer Image Analysis as a Method of Evaluating the Quality of Selected Fine-Grained Food Mixtures." Sustainability 13, no. 6 (March 10, 2021): 3018. http://dx.doi.org/10.3390/su13063018.
Full textAbstract:
This work presents the possibility of using computer image analysis to assess the quality of fine-grained food mixtures. The research was carried out using a mixture of wheat flour and algae. These types of ingredients are used, among others, to produce pasta, which is a functional food due to its enrichment with algae. The tests were carried out for mixtures with different shares of algae: 2%, 3% and 4% w/w. Mixing was carried out in a 3D mixer (Turbula® mixer), in which 20, 40 and 60 mL mixing vessels were placed. At the end of the process, samples were taken from four parts (sectors) of the mixing vessels, and then photos were taken with a digital camera. For this purpose, a specially prepared chamber was used, ensuring stable conditions for taking photos. The obtained images were analyzed in the Patan® program, determining the color on the RGB-256 scale. The obtained values were compared with the previously prepared reference specimen (simple linear regression formula). Based on this, it was possible to determine the share of algae in the samples taken and thus to estimate the homogeneity of the tested mixtures. The obtained results indicate the high reliability of the proposed solution.
29
Karavarsamis, Sotiris, Nikos Ntarmos, Konstantinos Blekas, and Ioannis Pitas. "Detecting Pornographic Images by Localizing Skin ROIs." International Journal of Digital Crime and Forensics 5, no. 1 (January 2013): 39–53. http://dx.doi.org/10.4018/jdcf.2013010103.
Full textAbstract:
In this study, a novel algorithm for recognizing pornographic images based on the analysis of skin color regions is presented. The skin color information essentially provides Regions of Interest (ROIs). It is demonstrated that the convex hull of these ROIs provides semantically useful information for pornographic image detection. Based on these convex hulls, the authors extract a small set of low-level visual features that are empirically proven to possess discriminative power for pornographic image classification. In this study, the authors consider multi-class pornographic image classification, where the “nude” and “benign” image classes are further split into two specialized sub-classes, namely “bikini”/”porn” and “skin”/”non-skin”, respectively. The extracted feature vectors are fed to an ensemble of random forest classifiers for image classification. Each classifier is trained on a partition of the training set and solves a binary classification problem. In this sense, the model allows for seamless coarse-to-fine-grained classification by means of a tree-structured topology of a small number of intervening binary classifiers. The overall technique is evaluated on the AIIA-PID challenge of 9,000 samples of pornographic and benign images. The technique is shown to exhibit state-of-the-art performance against publicly available integrated pornographic image classifiers.
30
Chen, Junwen, Zhiyi Chen, Simiao Tao, and Jing Xia. "Fine-grained Vehicle Classification Based on Feature Augmentation." Journal of Physics: Conference Series 2404, no. 1 (December 1, 2022): 012041. http://dx.doi.org/10.1088/1742-6596/2404/1/012041.
Full textAbstract:
Abstract Fine-grained vehicle classification is a hot research topic in the field of computer vision, which aims to recognize different models of vehicles belonging to the same brand. Limited by the large appearance differences of the same vehicle (due to different attitudes and perspectives) and small appearance differences between different vehicles, the vehicle’s reorganization performance is not high and can’t meet the real application requirements. In this paper, a Fine-grained Vehicle Classification is proposed based on Feature Augmentation (FAFCC), which focuses on mining the key discriminative parts of the object. Specifically, the FAFCC first improves the weakly supervised data augmentation network (WSDAN) by using multi-layer feature extraction and fusion instead of single-layer features. Further, the FAFCC assigns local feature weights to select key features, which can solve the problem that the discriminant features in the channel are not prominent enough and realize the high-quality compact fine-grained vehicle recognition task. The performance of the FAFCC on the fine-grained image classification tasks for vehicles has been evaluated through algorithm comparison experiments and ablation experiments. Through visual analysis, it can be seen that the introduction of each new module has optimized the loss function value and convergence speed of the model. In general, our FAFCC algorithm has a certain improvement effect compared with the original algorithm.
31
Wang, Libo, Rui Li, Dongzhi Wang, Chenxi Duan, Teng Wang, and Xiaoliang Meng. "Transformer Meets Convolution: A Bilateral Awareness Network for Semantic Segmentation of Very Fine Resolution Urban Scene Images." Remote Sensing 13, no. 16 (August 4, 2021): 3065. http://dx.doi.org/10.3390/rs13163065.
Full textAbstract:
Semantic segmentation from very fine resolution (VFR) urban scene images plays a significant role in several application scenarios including autonomous driving, land cover classification, urban planning, etc. However, the tremendous details contained in the VFR image, especially the considerable variations in scale and appearance of objects, severely limit the potential of the existing deep learning approaches. Addressing such issues represents a promising research field in the remote sensing community, which paves the way for scene-level landscape pattern analysis and decision making. In this paper, we propose a Bilateral Awareness Network which contains a dependency path and a texture path to fully capture the long-range relationships and fine-grained details in VFR images. Specifically, the dependency path is conducted based on the ResT, a novel Transformer backbone with memory-efficient multi-head self-attention, while the texture path is built on the stacked convolution operation. In addition, using the linear attention mechanism, a feature aggregation module is designed to effectively fuse the dependency features and texture features. Extensive experiments conducted on the three large-scale urban scene image segmentation datasets, i.e., ISPRS Vaihingen dataset, ISPRS Potsdam dataset, and UAVid dataset, demonstrate the effectiveness of our BANet. Specifically, a 64.6% mIoU is achieved on the UAVid dataset.
32
Knight, R. Klassen, P. Hunt, R. "Mineralogy of fine-grained sediment by energy-dispersive spectrometry (EDS) image analysis a methodology." Environmental Geology 42, no. 1 (May 1, 2002): 32–40. http://dx.doi.org/10.1007/s00254-002-0538-7.
Full text
33
Jiang, Xuexia, Tadamoto Isogai, Joseph Chi, and Gaudenz Danuser. "Fine-grained, nonlinear registration of live cell movies reveals spatiotemporal organization of diffuse molecular processes." PLOS Computational Biology 18, no. 12 (December 30, 2022): e1009667. http://dx.doi.org/10.1371/journal.pcbi.1009667.
Full textAbstract:
We present an application of nonlinear image registration to align in microscopy time lapse sequences for every frame the cell outline and interior with the outline and interior of the same cell in a reference frame. The registration relies on a subcellular fiducial marker, a cell motion mask, and a topological regularization that enforces diffeomorphism on the registration without significant loss of granularity. This allows spatiotemporal analysis of extremely noisy and diffuse molecular processes across the entire cell. We validate the registration method for different fiducial markers by measuring the intensity differences between predicted and original time lapse sequences of Actin cytoskeleton images and by uncovering zones of spatially organized GEF- and GTPase signaling dynamics visualized by FRET-based activity biosensors in MDA-MB-231 cells. We then demonstrate applications of the registration method in conjunction with stochastic time-series analysis. We describe distinct zones of locally coherent dynamics of the cytoplasmic protein Profilin in U2OS cells. Further analysis of the Profilin dynamics revealed strong relationships with Actin cytoskeleton reorganization during cell symmetry-breaking and polarization. This study thus provides a framework for extracting information to explore functional interactions between cell morphodynamics, protein distributions, and signaling in cells undergoing continuous shape changes. Matlab code implementing the proposed registration method is available at https://github.com/DanuserLab/Mask-Regularized-Diffeomorphic-Cell-Registration.
34
Wenk, Hans-Rudolf, Luca Lutterotti, Pamela Kaercher, Waruntorn Kanitpanyacharoen, Lowell Miyagi, and Roman Vasin. "Rietveld texture analysis from synchrotron diffraction images. II. Complex multiphase materials and diamond anvil cell experiments." Powder Diffraction 29, no. 3 (May 15, 2014): 220–32. http://dx.doi.org/10.1017/s0885715614000360.
Full textAbstract:
Synchrotron X-ray diffraction images are increasingly used to characterize crystallographic preferred orientation distributions (texture) of fine-grained polyphase materials. Diffraction images can be analyzed quantitatively with the Rietveld method as implemented in the software package Materials Analysis Using Diffraction. Here we describe the analysis procedure for diffraction images collected with high energy X-rays for a complex, multiphase shale, and for those collected in situ in diamond anvil cells at high pressure and anisotropic stress.
35
Park, M. H., Y. Tagusari, and N. Tsuji. "Characterization of local deformation and fracture behavior in ferrite + martensite dual-phase steels having different grain sizes." IOP Conference Series: Materials Science and Engineering 1249, no. 1 (July 1, 2022): 012041. http://dx.doi.org/10.1088/1757-899x/1249/1/012041.
Full textAbstract:
Abstract Low carbon dual-phase (DP) steels composed of soft ferrite and hard martensite have been widely used in the automotive industry due to their good strength-ductility balance and large strain hardening ability. DP steels have a wide variation in mechanical properties depending on several microstructural features such as grain size, phase fraction and distribution. Among them, the grain refinement of DP steels is known to be an effective option for enhancing mechanical performance in strength and ductility (especially post-uniform elongation). However, the exact reason for the significant improvement of post-uniform elongation by grain refinement has not been fully understood. It is considered that the characterization of local deformation behavior and micro-void formation/growth behavior in connection with microstructures is an essential approach for understanding the enhanced post-uniform elongation realized in the fine-grained DP specimen. In the present study, we prepared two kinds of DP specimens with mean ferrite grain sizes of 14.9 μm (coarse-grained DP) and 7.1 μm (fine-grained DP), and carefully investigated local strain distribution of tensile specimen and micro-void formation/growth behavior using digital image correlation (DIC) analysis and SEM observations. The fine-grained DP specimen exhibited a gradual strain localization after necking and had sufficient strain capacity that could endure against fracture. The fine-grained DP structure had a great number of micro-voids in the necked region, but almost all the micro-voids maintained a very small size, which was contrasted with the case of coarse-grained DP specimen containing very large-sized micro-voids. Such a significant difference in micro-void size/number characters between two kinds of DP specimens would be one possible reason for exhibiting greatly different post-uniform elongation behavior.
36
Dmitrieva, Maria A., Alina D. Kogai, Vladimir N. Leitsin, Aleksandr O. Tovpinets, and Maria V. Shinyaeva. "An experimental and theoretical approach to assessing the structure of fine-grained modified concretes." Vestnik MGSU, no. 1 (January 2023): 70–81. http://dx.doi.org/10.22227/1997-0935.2023.1.70-81.
Full textAbstract:
Introduction. The development of approaches to assessing structural characteristics of multicomponent modified concretes using non-destructive testing methods at all stages of hydration is a relevant means focused on ensuring optimal rheological and strength characteristics of concretes.
Materials and methods. Modified fine-grained concrete was analyzed as the material under study, since its composition meets the requirements of additive technologies applied in the construction industry. Modification was implemented by introducing additives and mechanically activating the initial cement-sand composition. The strength of resulting specimens was controlled as of the onset of curing. Structure formation was studied using a computed tomography scanner.
Results. A tomography data processing approach was developed to evaluate the modified concrete’s structure. Key aspects of the stage-by-stage processing of specimens’ images were identified and a solution was obtained for determining the threshold values of correspondence between image shades having different density structures. In the course of comparing the results of the strength and structure study, the value of the percentage ratio of inclusions was obtained for various densities during the curing process.
Conclusions. The proposed data acquisition approach contributes to development of further research in this area; it can become a stage in developing a new concrete structure analysis method. The study of specimens at early curing stages in combination with non-destructive control methods contributes to (1) development of rapid assessment techniques, applied to the quality of materials, and (2) an efficiency increase in the process of development.
37
Yan, Rui, Zhidong Yang, Jintao Li, Chunhou Zheng, and Fa Zhang. "Divide-and-Attention Network for HE-Stained Pathological Image Classification." Biology 11, no. 7 (June 29, 2022): 982. http://dx.doi.org/10.3390/biology11070982.
Full textAbstract:
Since pathological images have some distinct characteristics that are different from natural images, the direct application of a general convolutional neural network cannot achieve good classification performance, especially for fine-grained classification problems (such as pathological image grading). Inspired by the clinical experience that decomposing a pathological image into different components is beneficial for diagnosis, in this paper, we propose a Divide-and-Attention Network (DANet) for Hematoxylin-and-Eosin (HE)-stained pathological image classification. The DANet utilizes a deep-learning method to decompose a pathological image into nuclei and non-nuclei parts. With such decomposed pathological images, the DANet first performs feature learning independently in each branch, and then focuses on the most important feature representation through the branch selection attention module. In this way, the DANet can learn representative features with respect to different tissue structures and adaptively focus on the most important ones, thereby improving classification performance. In addition, we introduce deep canonical correlation analysis (DCCA) constraints in the feature fusion process of different branches. The DCCA constraints play the role of branch fusion attention, so as to maximize the correlation of different branches and ensure that the fused branches emphasize specific tissue structures. The experimental results of three datasets demonstrate the superiority of the DANet, with an average classification accuracy of 92.5% on breast cancer classification, 95.33% on colorectal cancer grading, and 91.6% on breast cancer grading tasks.
38
Dong, Qi, Xiatian Zhu, and Shaogang Gong. "Single-Label Multi-Class Image Classification by Deep Logistic Regression." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 3486–93. http://dx.doi.org/10.1609/aaai.v33i01.33013486.
Full textAbstract:
The objective learning formulation is essential for the success of convolutional neural networks. In this work, we analyse thoroughly the standard learning objective functions for multiclass classification CNNs: softmax regression (SR) for singlelabel scenario and logistic regression (LR) for multi-label scenario. Our analyses lead to an inspiration of exploiting LR for single-label classification learning, and then the disclosing of the negative class distraction problem in LR. To address this problem, we develop two novel LR based objective functions that not only generalise the conventional LR but importantly turn out to be competitive alternatives to SR in single label classification. Extensive comparative evaluations demonstrate the model learning advantages of the proposed LR functions over the commonly adopted SR in single-label coarse-grained object categorisation and cross-class fine-grained person instance identification tasks. We also show the performance superiority of our method on clothing attribute classification in comparison to the vanilla LR function. The code had been made publicly available.
39
Hoeser, Thorsten, Felix Bachofer, and Claudia Kuenzer. "Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review—Part II: Applications." Remote Sensing 12, no. 18 (September 18, 2020): 3053. http://dx.doi.org/10.3390/rs12183053.
Full textAbstract:
In Earth observation (EO), large-scale land-surface dynamics are traditionally analyzed by investigating aggregated classes. The increase in data with a very high spatial resolution enables investigations on a fine-grained feature level which can help us to better understand the dynamics of land surfaces by taking object dynamics into account. To extract fine-grained features and objects, the most popular deep-learning model for image analysis is commonly used: the convolutional neural network (CNN). In this review, we provide a comprehensive overview of the impact of deep learning on EO applications by reviewing 429 studies on image segmentation and object detection with CNNs. We extensively examine the spatial distribution of study sites, employed sensors, used datasets and CNN architectures, and give a thorough overview of applications in EO which used CNNs. Our main finding is that CNNs are in an advanced transition phase from computer vision to EO. Upon this, we argue that in the near future, investigations which analyze object dynamics with CNNs will have a significant impact on EO research. With a focus on EO applications in this Part II, we complete the methodological review provided in Part I.
40
Hossain, Sanoar, Saiyed Umer, Ranjeet Kr Rout, and M. Tanveer. "Fine-grained image analysis for facial expression recognition using deep convolutional neural networks with bilinear pooling." Applied Soft Computing 134 (February 2023): 109997. http://dx.doi.org/10.1016/j.asoc.2023.109997.
Full text
41
Hao, Xia, Man Zhang, Tianru Zhou, Xuchao Guo, Federico Tomasetto, Yuxin Tong, and Minjuan Wang. "An Automatic Light Stress Grading Architecture Based on Feature Optimization and Convolutional Neural Network." Agriculture 11, no. 11 (November 11, 2021): 1126. http://dx.doi.org/10.3390/agriculture11111126.
Full textAbstract:
The identification of light stress is crucial for light control in plant factories. Image-based lighting classification of leafy vegetables has exhibited remarkable performance with high convenience and economy. Convolutional Neural Network (CNN) has been widely used for crop image analysis because of its architecture, high accuracy and efficiency. Among them, large intra-class differences and small inter-class differences are important factors affecting crop identification and a critical challenge for fine-grained classification tasks based on CNN. To address this problem, we took the Lettuce (Lactuca sativa L.) widely grown in plant factories as the research object and constructed a leaf image set containing four stress levels. Then a light stress grading model combined with classic pre-trained CNN and Triplet loss function is constructed, which is named Tr-CNN. The model uses the Triplet loss function to constrain the distance of images in the feature space, which can reduce the Euclidean distance of the samples from the same class and increase the heterogeneous Euclidean distance. Multiple sets of experimental results indicate that the model proposed in this paper (Tr-CNN) has obvious advantages in light stress grading dataset and generalized dataset.
42
Richardson, Ian Reginald, David Neil Chapman, and Stephen Brown. "Relating Failure Tests Performed in Hollow Cylinder Apparatus to Inherent Anisotropy." Transportation Research Record: Journal of the Transportation Research Board 1526, no. 1 (January 1996): 149–56. http://dx.doi.org/10.1177/0361198196152600119.
Full textAbstract:
Described are failure tests performed on a fine-grained Leighton Buzzard sand in the Nottingham hollow cylinder apparatus. These tests were conducted to characterize the inherent anisotropy of the material formed during the sample preparation procedure. An image analysis procedure for determining preferred particle orientation is introduced and its derivation discussed. An attempt is subsequently made to relate the statistically significant preferred orientation to the anisotropic shear strength properties of the Leighton Buzzard sand.
43
Wang, Jian, Xian-Hua Han, Yingying Xu, Lanfen Lin, Hongjie Hu, Chongwu Jin, and Yen-Wei Chen. "Sparse Codebook Model of Local Structures for Retrieval of Focal Liver Lesions Using Multiphase Medical Images." International Journal of Biomedical Imaging 2017 (2017): 1–13. http://dx.doi.org/10.1155/2017/1413297.
Full textAbstract:
Characterization and individual trait analysis of the focal liver lesions (FLL) is a challenging task in medical image processing and clinical site. The character analysis of a unconfirmed FLL case would be expected to benefit greatly from the accumulated FLL cases with experts’ analysis, which can be achieved by content-based medical image retrieval (CBMIR). CBMIR mainly includes discriminated feature extraction and similarity calculation procedures. Bag-of-Visual-Words (BoVW) (codebook-based model) has been proven to be effective for different classification and retrieval tasks. This study investigates an improved codebook model for the fined-grained medical image representation with the following three advantages: (1) instead of SIFT, we exploit the local patch (structure) as the local descriptor, which can retain all detailed information and is more suitable for the fine-grained medical image applications; (2) in order to more accurately approximate any local descriptor in coding procedure, the sparse coding method, instead of K-means algorithm, is employed for codebook learning and coded vector calculation; (3) we evaluate retrieval performance of focal liver lesions (FLL) using multiphase computed tomography (CT) scans, in which the proposed codebook model is separately learned for each phase. The effectiveness of the proposed method is confirmed by our experiments on FLL retrieval.
44
Dearnley, R. "Effects of resolution on the measurement of grain ‘size’." Mineralogical Magazine 49, no. 353 (September 1985): 539–46. http://dx.doi.org/10.1180/minmag.1985.049.353.07.
Full textAbstract:
AbstractMeasurements of fine-grained dolerites by optical automatic image analysis are used to illustrate the effects of magnification and resolution on the values obtained for grain ‘size’, grain boundary length, surface area per unit volume, and other parameters. Within the measured range of optical magnifications (× 26 to × 3571) and resolutions (1.20 × 10−3 cm to 8.50 × 10−6 cm), it is found that the values of all grain parameters estimated by chord size analysis vary with magnification. These results are interpreted in terms of the concepts of ‘fractal dimensions’ introduced by Mandelbrot (1967, 1977). For some comparative purposes the fractal relationships may be of little significance as relative changes of size, surface area, and other parameters can be expressed adequately at given magnification(s). But for many studies, for instance in kinetics of grain growth, the actual diameter or surface area per unit volume is an important dimension. The consequences are disconcerting and suggest that it may be difficult in some instances to specify the ‘true’ measurements of various characteristics of fine-grained aggregates.
45
Imae, Naoya. "Cometary dust in Antarctic micrometeorites." Proceedings of the International Astronomical Union 8, S288 (August 2012): 123–29. http://dx.doi.org/10.1017/s1743921312016766.
Full textAbstract:
AbstractCometary nuclei consist of aggregates of interstellar dust particles less than ~1 μm in diameter and can produce rocky dust particles as a result of the sublimation of ice as comets enter the inner solar system. Samples of fine-grained particles known as chondritic porous interplanetary dust particles (CP-IDPs), possibly from comets, have been collected from the Earth's stratosphere. Owing to their fine-grained texture, these particles were previously thought to be condensates formed directly from interstellar gas. However, coarse-grained chondrule-like objects have recently been observed in samples from comet 81P/Wild 2. The chondrule-like objects are chemically distinct from chondrules in meteoritic chondrites, possessing higher MnO contents (0.5 wt%) in olivine and low-Ca pyroxene. In this study, we analyzed AMM samples by secondary electron microscopy and backscattered electron images for textural observations and compositional analysis. We identified thirteen AMMs with characteristics similar to those of the 81P/Wild 2 samples, and believe that recognition of these similarities necessitates reassessment of the existing models of chondrule formation.
46
Hui, Ruan. "Video Content Analysis of Human Sports under Engineering Management Incorporating High-Level Semantic Recognition Models." Computational Intelligence and Neuroscience 2022 (January 12, 2022): 1–12. http://dx.doi.org/10.1155/2022/6761857.
Full textAbstract:
In this paper, a high-level semantic recognition model is used to parse the video content of human sports under engineering management, and the stream shape of the previous layer is embedded in the convolutional operation of the next layer, so that each layer of the convolutional neural network can effectively maintain the stream structure of the previous layer, thus obtaining a video image feature representation that can reflect the image nearest neighbor relationship and association features. The method is applied to image classification, and the experimental results show that the method can extract image features more effectively, thus improving the accuracy of feature classification. Since fine-grained actions usually share a very high similarity in phenotypes and motion patterns, with only minor differences in local regions, inspired by the human visual system, this paper proposes integrating visual attention mechanisms into the fine-grained action feature extraction process to extract features for cues. Taking the problem as the guide, we formulate the athlete’s tacit knowledge management strategy and select the distinctive freestyle aerial skills national team as the object of empirical analysis, compose a more scientific and organization-specific tacit knowledge management program, exert influence on the members in the implementation, and revise to form a tacit knowledge management implementation program with certain promotion value. Group behavior can be identified by analyzing the behavior of individuals and the interaction information between individuals. Individual interactions in a group can be represented by individual representations, and the relationship between individual behaviors can be analyzed by modeling the relationship between individual representations. The performance improvement of the method on mismatched datasets is comparable between the long-short time network based on temporal information and the language recognition method with high-level semantic embedding vectors, with the two methods improving about 12.6% and 23.0%, respectively, compared with the method using the original model and with the i-vector baseline system based on the support vector machine classification method with radial basis functions, with performance improvements about 10.10% and 10.88%, respectively.
47
Fieraru, Mihai, Mihai Zanfir, Elisabeta Oneata, Alin-Ionut Popa, Vlad Olaru, and Cristian Sminchisescu. "Learning Complex 3D Human Self-Contact." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 2 (May 18, 2021): 1343–51. http://dx.doi.org/10.1609/aaai.v35i2.16223.
Full textAbstract:
Monocular estimation of three dimensional human self-contact is fundamental for detailed scene analysis including body language understanding and behaviour modeling. Existing 3d reconstruction methods do not focus on body regions in self-contact and consequently recover configurations that are either far from each other or self-intersecting, when they should just touch. This leads to perceptually incorrect estimates and limits impact in those very fine-grained analysis domains where detailed 3d models are expected to play an important role. To address such challenges we detect self-contact and design 3d losses to explicitly enforce it. Specifically, we develop a model for Self-Contact Prediction (SCP), that estimates the body surface signature of self-contact, leveraging the localization of self-contact in the image, during both training and inference. We collect two large datasets to support learning and evaluation: (1) HumanSC3D, an accurate 3d motion capture repository containing 1,032 sequences with 5,058 contact events and 1,246,487 ground truth 3d poses synchronized with images collected from multiple views, and (2) FlickrSC3D, a repository of 3,969 images, containing 25,297 surface-to-surface correspondences with annotated image spatial support. We also illustrate how more expressive 3d reconstructions can be recovered under self-contact signature constraints and present monocular detection of face-touch as one of the multiple applications made possible by more accurate self-contact models.
48
Wang, Linfeng, Heng Wan, Deqing Huang, Jiayao Liu, Xuliang Tang, and Linfeng Gan. "Sustainable Analysis of Insulator Fault Detection Based on Fine-Grained Visual Optimization." Sustainability 15, no. 4 (February 14, 2023): 3456. http://dx.doi.org/10.3390/su15043456.
Full textAbstract:
Insulators of the kind used for overhead transmission lines institute important kinds of insulation control, namely, electrical insulation and mechanical fixing. Because of their large exposure to the environment, they are affected by factors such as climate, temperature, durability, the easy occurrence of explosions, damage, the threat of going missing, and other faults. These seriously influence the safety of the power transmission, so insulation monitoring must be conducted. With the development of unmanned technology, the staff used unmanned aircraft to take aerial photos of the detected insulators, and the insulator images were obtained by naked eye observation. Although this method looks very reliable, in practice, due to the large quantity of insulator-collected seismic data, and the complex background, workers are usually relying on their experience to make judgements, so it is easy for mistakes to appear. In recent years, with the rapid development of computer technology, more and more attention has been paid to fault detection and identification in insulators by computer-aided workers. In order to improve the detection accuracy of self-exploding insulators, especially in bad weather environments, and to overcome the influence of fog on target detection, a regression attention convolutional neural network is used for optimization. Through the recursive operation of multi-scale attention, multi-scale feature information is connected in series, the regional focus is recursively generated from coarse to fine, and the target region is detected to achieve optimal results. The experimental results show that the proposed method can effectively improve the fault diagnosis ability of insulators. Compared with the accuracy of other basic models, such as FCAN and MG-CNN, the accuracy of RA-CNN in multi-layer cascade optimization is higher than that in the previous two models, which is 74.9% and 75.6%, respectively. In addition, the results of the ablation experiments at different scales showed that the identification results of different two-level combinations were 78.2%, 81.4%, and 83.6%, and the accuracy of selecting three-level combinations was up to 85.3%, which was significantly higher than the other models.
49
Zhao, Ling, Li Luo, Bo Li, Liyan Xu, Jiawei Zhu, Silu He, and Haifeng Li. "Analysis of the Uniqueness and Similarity of City Landscapes Based on Deep Style Learning." ISPRS International Journal of Geo-Information 10, no. 11 (October 29, 2021): 734. http://dx.doi.org/10.3390/ijgi10110734.
Full textAbstract:
The city landscape is largely related to the design concept and aesthetics of planners. Influenced by globalization, planners and architects have borrowed from available designs, resulting in the “one city with a thousand faces” phenomenon. In order to create a unique urban landscape, they need to focus on local urban characteristics while learning new knowledge. Therefore, it is particularly important to explore the characteristics of cities’ landscapes. Previous researchers have studied them from different perspectives through social media data such as element types and feature maps. They only considered the content information of a image. However, social media images themselves have a “photographic cultural” character, which affects the city character. Therefore, we introduce this characteristic and propose a deep style learning for the city landscape method that can learn the global landscape features of cities from massive social media images encoded as vectors called city style features (CSFs). We find that CSFs can describe two landscape features: (1) intercity landscape features, which can quantitatively assess the similarity of intercity landscapes (we find that cities in close geographical proximity tend to have greater visual similarity to each other), and (2) intracity landscape features, which contain the inherent style characteristics of cities, and more fine-grained internal-city style characteristics can be obtained through cluster analysis. We validate the effectiveness of the above method on over four million Flickr social media images. The method proposed in this paper also provides a feasible approach for urban style analysis.
50
Lu, Chenggang, Zhitao Guo, Jinli Yuan, Kewen Xia, and Hengyong Yu. "Fine-grained calibrated double-attention convolutional network for left ventricular segmentation." Physics in Medicine & Biology 67, no. 5 (March 3, 2022): 055013. http://dx.doi.org/10.1088/1361-6560/ac5570.
Full textAbstract:
Abstract Objective. Left ventricular (LV) segmentation of cardiac magnetic resonance imaging (MRI) is essential for diagnosing and treating the early stage of heart diseases. In convolutional neural networks, the target information of the LV in feature maps may be lost with convolution and max-pooling, particularly at the end of systolic. Fine segmentation of ventricular contour is still a challenge, and it may cause problems with inaccurate calculation of clinical parameters (e.g. ventricular volume). In order to improve the similarity of the neural network output and the target segmentation region, in this paper, a fine-grained calibrated double-attention convolutional network (FCDA-Net) is proposed to finely segment the endocardium and epicardium from ventricular MRI. Approach. FCDA-Net takes the U-net as the backbone network, and the encoder-decoder structure incorporates a double grouped-attention module that is constructed by a fine calibration spatial attention module (fcSAM) and a fine calibration channel attention module (fcCAM). The double grouped-attention mechanism enhances the expression of information in both spatial and channelwise feature maps to achieve fine calibration. Main Results. The proposed approach is evaluated on the public MICCAI 2009 challenge dataset, and ablation experiments are conducted to demonstrate the effect of each grouped-attention module. Compared with other advanced segmentation methods, FCDA-Net can obtain better LV segmentation performance. Significance. The LV segmentation results of MRI can be used to perform more accurate quantitative analysis of many essential clinical parameters and it can play an important role in image-guided clinical surgery.