Journal articles: 'Computer vision; robust model fitting; preference'

1

Zhao, Xi, Yun Zhang, Shoulie Xie, Qianqing Qin, Shiqian Wu, and Bin Luo. "Outlier Detection Based on Residual Histogram Preference for Geometric Multi-Model Fitting." Sensors 20, no. 11 (May 27, 2020): 3037. http://dx.doi.org/10.3390/s20113037.

Full text

Abstract:

Geometric model fitting is a fundamental issue in computer vision, and the fitting accuracy is affected by outliers. In order to eliminate the impact of the outliers, the inlier threshold or scale estimator is usually adopted. However, a single inlier threshold cannot satisfy multiple models in the data, and scale estimators with a certain noise distribution model work poorly in geometric model fitting. It can be observed that the residuals of outliers are big for all true models in the data, which makes the consensus of the outliers. Based on this observation, we propose a preference analysis method based on residual histograms to study the outlier consensus for outlier detection in this paper. We have found that the outlier consensus makes the outliers gather away from the inliers on the designed residual histogram preference space, which is quite convenient to separate outliers from inliers through linkage clustering. After the outliers are detected and removed, a linkage clustering with permutation preference is introduced to segment the inliers. In addition, in order to make the linkage clustering process stable and robust, an alternative sampling and clustering framework is proposed in both the outlier detection and inlier segmentation processes. The experimental results also show that the outlier detection scheme based on residual histogram preference can detect most of the outliers in the data sets, and the fitting results are better than most of the state-of-the-art methods in geometric multi-model fitting.

APA, Harvard, Vancouver, ISO, and other styles

2

Wang, Hanzi, and David Suter. "Using symmetry in robust model fitting." Pattern Recognition Letters 24, no. 16 (December 2003): 2953–66. http://dx.doi.org/10.1016/s0167-8655(03)00156-9.

Full text

APA, Harvard, Vancouver, ISO, and other styles

3

Wang, Yiru, Yinlong Liu, Xuechen Li, Chen Wang, Manning Wang, and Zhijian Song. "GORFLM: Globally Optimal Robust Fitting for Linear Model." Signal Processing: Image Communication 84 (May 2020): 115834. http://dx.doi.org/10.1016/j.image.2020.115834.

Full text

APA, Harvard, Vancouver, ISO, and other styles

4

Pham, Trung T., Tat-Jun Chin, Jin Yu, and David Suter. "The Random Cluster Model for Robust Geometric Fitting." IEEE Transactions on Pattern Analysis and Machine Intelligence 36, no. 8 (August 2014): 1658–71. http://dx.doi.org/10.1109/tpami.2013.2296310.

Full text

APA, Harvard, Vancouver, ISO, and other styles

5

Zhang, Zongliang, Jonathan Li, Yulan Guo, Xin Li, Yangbin Lin, Guobao Xiao, and Cheng Wang. "Robust procedural model fitting with a new geometric similarity estimator." Pattern Recognition 85 (January 2019): 120–31. http://dx.doi.org/10.1016/j.patcog.2018.07.027.

Full text

APA, Harvard, Vancouver, ISO, and other styles

6

Wimmer, M., F. Stulp, S. Pietzsch, and B. Radig. "Learning Local Objective Functions for Robust Face Model Fitting." IEEE Transactions on Pattern Analysis and Machine Intelligence 30, no. 8 (August 2008): 1357–70. http://dx.doi.org/10.1109/tpami.2007.70793.

Full text

APA, Harvard, Vancouver, ISO, and other styles

7

WANG, HAI-JUN, and MING LIU. "ACTIVE CONTOURS DRIVEN BY LOCAL GAUSSIAN DISTRIBUTION FITTING ENERGY BASED ON LOCAL ENTROPY." International Journal of Pattern Recognition and Artificial Intelligence 27, no. 06 (September 2013): 1355008. http://dx.doi.org/10.1142/s0218001413550082.

Full text

Abstract:

This paper presents a scheme of improvement on the local Gaussian distribution fitting energy (LGDF) model in terms of robustness to initialization and noise. The LGDF energy is redefined as a weighted energy integral. The weights are defined based on local entropy deriving from a gray level distribution of local image, which enables the proposed model to be robust to the initialization. Experimental results prove that the proposed model is more robustness to noise than the original LGDF model, local binary fitting (LBF) model and local image fitting (LIF) model.

APA, Harvard, Vancouver, ISO, and other styles

8

Wong, Hoi Sim, Tat-Jun Chin, Jin Yu, and David Suter. "A simultaneous sample-and-filter strategy for robust multi-structure model fitting." Computer Vision and Image Understanding 117, no. 12 (December 2013): 1755–69. http://dx.doi.org/10.1016/j.cviu.2013.08.007.

Full text

APA, Harvard, Vancouver, ISO, and other styles

9

Wang, Hanzi, and David Suter. "MDPE: A Very Robust Estimator for Model Fitting and Range Image Segmentation." International Journal of Computer Vision 59, no. 2 (September 2004): 139–66. http://dx.doi.org/10.1023/b:visi.0000022287.61260.b0.

Full text

APA, Harvard, Vancouver, ISO, and other styles

10

Verma, Rachna, and Arvind Kumar Verma. "A Clustering and Outlier Detection Scheme for Robust Parametric Model Estimation for Plane Fitting." Applied Mechanics and Materials 789-790 (September 2015): 770–75. http://dx.doi.org/10.4028/www.scientific.net/amm.789-790.770.

Full text

Abstract:

Extraction of geometric information and reconstruction of a parametric model from the data points captured by various sensors or generated by various image preprocessing algorithms is a vital research issue for many computer vision and robotics applications. The aim is to reconstruct 3D objects, consisting of planar patches, in a scene from its point cloud captured by a sensor set. A reconstructed scene has many applications such as stereo vision, robot navigation, medical imaging, etc. Unfortunately, the captured point cloud often gets corrupted due to sensor errors/malfunctioning and preprocessing algorithms. The corrupted data pose difficulty in accurate estimation of underlying geometric model parameters. In this paper, a new algorithm has been proposed to efficiently and accurately estimate the model parameters in heavily corrupted data points. The method is based on forming clusters of estimated planes with reference to a fixed plane. Clustering is accomplished on the basis of angles and distances of estimated planes from the reference plane. The proposed method is implemented over a wide range of data points. It is a robust technique and observed to outperform the widely used RANSAC algorithm in terms of accuracy and computational efficiency.

APA, Harvard, Vancouver, ISO, and other styles

11

Yu, Yong Yan. "Estimate the Performance of Multi-Model Estimation Algorithms." Applied Mechanics and Materials 427-429 (September 2013): 1506–9. http://dx.doi.org/10.4028/www.scientific.net/amm.427-429.1506.

Full text

Abstract:

A robust estimation procedure is necessary to estimate the true model parameters in computer vision. Evaluating the multiple-model in the presence of outliers-robust is a fundamentally different task than the single-model problem.Despite there are many diversity multi-model estimation algorithms, it is difficult to pick an effective and advisably approach.So we present a novel quantitative evaluation of multi-model estimation algorithms, efficiency may be evaluated by either examining the asymptotic efficiency of the algorithms or by running them for a series of data sets of increasing size.Thus we create a specifical testing dataset,and introduce a performance metric, Strongest-Intersection.and using the model-aware correctness criterion. Finally, well show the validity of estimation strategy by the Experimention of line-fitting.

APA, Harvard, Vancouver, ISO, and other styles

12

Cao, Hui Rong, and Fu Chang Wang. "Integer-Coded Genetic Algorithm for Trimmed Estimator of Multivariate Linear Errors in Variables Model." Advanced Materials Research 457-458 (January 2012): 1223–29. http://dx.doi.org/10.4028/www.scientific.net/amr.457-458.1223.

Full text

Abstract:

The multivariate linear errors-in-variables (EIV) model is frequently used in computer vision for model fitting tasks. As well known, when sample data is contaminated by large numbers of awkwardly placed outliers, the least squares estimator isn’t robust. To obtain robust estimators of multivariate linear EIV model, orthogonal least trimmed square and orthogonal least trimmed absolute deviation estimators based on the subset of h cases(out of n)are proposed. However, these robust estimators possessing the exact fit property are NP-hard to compute. To tackle this problem, an integer-coded genetic algorithm that is applicable to trimmed estimators is presented. The trimmed estimators of multivariate linear EIV model on real data are provided and the results show that the integer-coded genetic algorithm is correct and effective.

APA, Harvard, Vancouver, ISO, and other styles

13

Zhou, Kai, Karthik Mahesh Varadarajan, Michael Zillich, and Markus Vincze. "Gaussian-weighted Jensen–Shannon divergence as a robust fitness function for multi-model fitting." Machine Vision and Applications 24, no. 6 (May 17, 2013): 1107–19. http://dx.doi.org/10.1007/s00138-013-0513-1.

Full text

APA, Harvard, Vancouver, ISO, and other styles

14

Rodziewicz-Bielewicz, Jan, and Marcin Korzeń. "Comparison of Graph Fitting and Sparse Deep Learning Model for Robot Pose Estimation." Sensors 22, no. 17 (August 29, 2022): 6518. http://dx.doi.org/10.3390/s22176518.

Full text

Abstract:

The paper presents a simple, yet robust computer vision system for robot arm tracking with the use of RGB-D cameras. Tracking means to measure in real time the robot state given by three angles and with known restrictions about the robot geometry. The tracking system consists of two parts: image preprocessing and machine learning. In the machine learning part, we compare two approaches: fitting the robot pose to the point cloud and fitting the convolutional neural network model to the sparse 3D depth images. The advantage of the presented approach is direct use of the point cloud transformed to the sparse image in the network input and use of sparse convolutional and pooling layers (sparse CNN). The experiments confirm that the robot tracking is performed in real time and with an accuracy comparable to the accuracy of the depth sensor.

APA, Harvard, Vancouver, ISO, and other styles

15

Jeni, Laszlo A., Hideki Hashimoto, and Takashi Kubota. "Robust Facial Expression Recognition Using Near Infrared Cameras." Journal of Advanced Computational Intelligence and Intelligent Informatics 16, no. 2 (March 20, 2012): 341–48. http://dx.doi.org/10.20965/jaciii.2012.p0341.

Full text

Abstract:

In human-human communication we use verbal, vocal and non-verbal signals to communicate with others. Facial expressions are a form of non-verbal communication, recognizing them helps to improve the human-machine interaction. This paper proposes a system for pose- and illumination-invariant recognition of facial expressions using near-infrared camera images and precise 3D shape registration. Precise 3D shape information of the human face can be computed by means of Constrained Local Models (CLM), which fits a dense model to an unseen image in an iterative manner. We used a multi-class SVM to classify the acquired 3D shape into different emotion categories. Results surpassed human performance and show poseinvariant performance. Varying lighting conditions can influence the fitting process and reduce the recognition precision. We built a near-infrared and visible light camera array to test the method with different illuminations. Results shows that the near-infrared camera configuration is suitable for robust and reliable facial expression recognition with changing lighting conditions.

APA, Harvard, Vancouver, ISO, and other styles

16

Jiang, Xiao Liang, Bai Lin Li, Jian Ying Yuan, and Xiao Liang Wu. "Active Contour Driven by Local Gaussian Distribution Fitting and Local Signed Difference Based on Local Entropy." International Journal of Pattern Recognition and Artificial Intelligence 30, no. 03 (February 22, 2016): 1655011. http://dx.doi.org/10.1142/s0218001416550119.

Full text

Abstract:

Intensity inhomogeneity often causes considerable difficulties in image segmentation. In order to tackle this problem, we propose a novel region-based active contour model in a variational level set formulation. We first define a data fitting energy with a local Gaussian distribution fitting (LGDF) term, which induces a local force to attract the contour and stops it at object boundaries, and a local signed difference (LSD) term based on local entropy, which possesses both local separability and global consistency. This energy is then incorporated into a level set formulation with a level set regularization term that is necessary for accurate computation in the corresponding level set method. Experimental results show that the proposed model can not only segment images with intensity inhomogeneities and weak boundaries but also be robust to the noise, initial contours.

APA, Harvard, Vancouver, ISO, and other styles

17

Wang, Xinmei, Zhenzhu Liu, Feng Liu, and Leimin Wang. "The Estimation of Image Jacobian Matrix with Time-Delay Compensation." Journal of Advanced Computational Intelligence and Intelligent Informatics 25, no. 6 (November 20, 2021): 982–88. http://dx.doi.org/10.20965/jaciii.2021.p0982.

Full text

Abstract:

Time delay exists in image-based visual servo system, which will have a certain impact on the system control. To solve the impact of time delay, the time delay compensation of the object feature point image and the image Jacobian matrix is discussed in this paper. Some work is done in this paper: The estimation of the object feature point image under time delay is based on a proposed robust decorrelation Kalman filtering model, for the measurement vectors which cannot be obtained during time delay in the robust Kalman filtering model, a polynomial fitting method is proposed in which the selection of the polynomial includes the position, velocity and acceleration of the object feature point which impact the feature point trajectory, then the more accurate object feature point image can be obtained. From the estimated object feature point image under time delay, the more accurate image Jacobian matrix under time delay can be obtained. Simulation and experimental results verify the feasibility and superiority of this paper method.

APA, Harvard, Vancouver, ISO, and other styles

18

Lei, Yu, and Guirong Weng. "A robust hybrid active contour model based on pre-fitting bias field correction for fast image segmentation." Signal Processing: Image Communication 97 (September 2021): 116351. http://dx.doi.org/10.1016/j.image.2021.116351.

Full text

APA, Harvard, Vancouver, ISO, and other styles

19

Fu, Qinbing, and Shigang Yue. "Modelling Drosophila motion vision pathways for decoding the direction of translating objects against cluttered moving backgrounds." Biological Cybernetics 114, no. 4-5 (July 4, 2020): 443–60. http://dx.doi.org/10.1007/s00422-020-00841-x.

Full text

Abstract:

Abstract Decoding the direction of translating objects in front of cluttered moving backgrounds, accurately and efficiently, is still a challenging problem. In nature, lightweight and low-powered flying insects apply motion vision to detect a moving target in highly variable environments during flight, which are excellent paradigms to learn motion perception strategies. This paper investigates the fruit fly Drosophila motion vision pathways and presents computational modelling based on cutting-edge physiological researches. The proposed visual system model features bio-plausible ON and OFF pathways, wide-field horizontal-sensitive (HS) and vertical-sensitive (VS) systems. The main contributions of this research are on two aspects: (1) the proposed model articulates the forming of both direction-selective and direction-opponent responses, revealed as principal features of motion perception neural circuits, in a feed-forward manner; (2) it also shows robust direction selectivity to translating objects in front of cluttered moving backgrounds, via the modelling of spatiotemporal dynamics including combination of motion pre-filtering mechanisms and ensembles of local correlators inside both the ON and OFF pathways, which works effectively to suppress irrelevant background motion or distractors, and to improve the dynamic response. Accordingly, the direction of translating objects is decoded as global responses of both the HS and VS systems with positive or negative output indicating preferred-direction or null-direction translation. The experiments have verified the effectiveness of the proposed neural system model, and demonstrated its responsive preference to faster-moving, higher-contrast and larger-size targets embedded in cluttered moving backgrounds.

APA, Harvard, Vancouver, ISO, and other styles

20

Buongiorno, Domenico, Donato Caramia, Luca Di Ruscio, Nicola Longo, Simone Panicucci, Giovanni Di Stefano, Vitoantonio Bevilacqua, and Antonio Brunetti. "Object Detection for Industrial Applications: Training Strategies for AI-Based Depalletizer." Applied Sciences 12, no. 22 (November 15, 2022): 11581. http://dx.doi.org/10.3390/app122211581.

Full text

Abstract:

In the last 10 years, the demand for robot-based depalletization systems has constantly increased due to the growth of sectors such as logistics, storage, and supply chains. Since the scenarios are becoming more and more unstructured, characterized by unknown pallet layouts and stock-keeping unit shapes, the classical depalletization systems based on the knowledge of predefined positions within the pallet frame are going to be substituted by innovative and robust solutions based on 2D/3D vision and Deep Learning (DL) methods. In particular, the Convolutional Neural Networks (CNNs) are deep networks that have proven to be effective in processing 2D/3D images, for example in the automatic object detection task, and robust to the possible variability among the data. However, deep neural networks need a big amount of data to be trained. In this context, whenever deep networks are involved in object detection for supporting depalletization systems, the dataset collection represents one of the main bottlenecks during the commissioning phase. The present work aims at comparing different training strategies to customize an object detection model aiming at minimizing the number of images required for model fitting, while ensuring reliable and robust performances. Different approaches based on a CNN for object detection are proposed, evaluated, and compared in terms of the F1-score. The study was conducted considering different starting conditions in terms of the neural network’s weights, the datasets, and the training set sizes. The proposed approaches were evaluated on the detection of different kinds of paper boxes placed on an industrial pallet. The outcome of the work validates that the best strategy is based on fine-tuning of a CNN-based model already trained on the detection of paper boxes, with a median F1-score greater than 85.0%.

APA, Harvard, Vancouver, ISO, and other styles

21

Huang, R., W. Yao, Z. Ye, Y. Xu, and U. Stilla. "RIDF: A ROBUST ROTATION-INVARIANT DESCRIPTOR FOR 3D POINT CLOUD REGISTRATION IN THE FREQUENCY DOMAIN." ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences V-2-2020 (August 3, 2020): 235–42. http://dx.doi.org/10.5194/isprs-annals-v-2-2020-235-2020.

Full text

Abstract:

Abstract. Registration of point clouds is a fundamental problem in the community of photogrammetry and 3D computer vision. Generally, point cloud registration consists of two steps: the search of correspondences and the estimation of transformation parameters. However, to find correspondences from point clouds, generating robust and discriminative features is of necessity. In this paper, we address the problem of extracting robust rotation-invariant features for fast coarse registration of point clouds under the assumption that the pairwise point clouds are transformed with rigid transformation. With a Fourier-based descriptor, point clouds represented by volumetric images can be mapped from the image to feature space. It is achieved by considering a gradient histogram as a continuous angular signal which can be well represented by the spherical harmonics. The rotation-invariance is established based on the Fourier-based analysis, in which high-frequency signals can be filtered out. This makes the extracted features robust to noises and outliers. Then, with the extracted features, pairwise correspondence can be found by the fast search. Finally, the transformation parameters can be estimated by fitting the rigid transformation model using the corresponding points and RANSAC algorithm. Experiments are conducted to prove the effectiveness of our proposed method in the task of point cloud registration. Regarding the experimental results of the point cloud registration using two TLS benchmark point cloud datasets, featuring with limited overlaps and uneven point densities and covering different urban scenes, our proposed method can achieve a fast coarse registration with rotation errors of less than 1 degree and translation errors of less than 1m.

APA, Harvard, Vancouver, ISO, and other styles

22

Mundt, Martin, Iuliia Pliushch, Sagnik Majumder, Yongwon Hong, and Visvanathan Ramesh. "Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition." Journal of Imaging 8, no. 4 (March 31, 2022): 93. http://dx.doi.org/10.3390/jimaging8040093.

Full text

Abstract:

Modern deep neural networks are well known to be brittle in the face of unknown data instances and recognition of the latter remains a challenge. Although it is inevitable for continual-learning systems to encounter such unseen concepts, the corresponding literature appears to nonetheless focus primarily on alleviating catastrophic interference with learned representations. In this work, we introduce a probabilistic approach that connects these perspectives based on variational inference in a single deep autoencoder model. Specifically, we propose to bound the approximate posterior by fitting regions of high density on the basis of correctly classified data points. These bounds are shown to serve a dual purpose: unseen unknown out-of-distribution data can be distinguished from already trained known tasks towards robust application. Simultaneously, to retain already acquired knowledge, a generative replay process can be narrowed to strictly in-distribution samples, in order to significantly alleviate catastrophic interference.

APA, Harvard, Vancouver, ISO, and other styles

23

Yang, Fengwei, Chandrasekhar Venkataraman, Sai Gu, Vanessa Styles, and Anotida Madzvamuse. "Force Estimation during Cell Migration Using Mathematical Modelling." Journal of Imaging 8, no. 7 (July 15, 2022): 199. http://dx.doi.org/10.3390/jimaging8070199.

Full text

Abstract:

Cell migration is essential for physiological, pathological and biomedical processes such as, in embryogenesis, wound healing, immune response, cancer metastasis, tumour invasion and inflammation. In light of this, quantifying mechanical properties during the process of cell migration is of great interest in experimental sciences, yet few theoretical approaches in this direction have been studied. In this work, we propose a theoretical and computational approach based on the optimal control of geometric partial differential equations to estimate cell membrane forces associated with cell polarisation during migration. Specifically, cell membrane forces are inferred or estimated by fitting a mathematical model to a sequence of images, allowing us to capture dynamics of the cell migration. Our approach offers a robust and accurate framework to compute geometric mechanical membrane forces associated with cell polarisation during migration and also yields geometric information of independent interest, we illustrate one such example that involves quantifying cell proliferation levels which are associated with cell division, cell fusion or cell death.

APA, Harvard, Vancouver, ISO, and other styles

24

Li, Bin, Qiyu He, Xiaopeng Liu, Yajun Jiang, and Zhigang Hu. "A joint structure of multi-distance based metric learning for person re-identification." Journal of Intelligent & Fuzzy Systems 41, no. 6 (December 16, 2021): 6629–39. http://dx.doi.org/10.3233/jifs-210505.

Full text

Abstract:

Person re-identification problem is a valuable computer vision task, which aims at matching pedestrian images of different cameras in a non-overlapping surveillance network. Existing metric learning based methods address this problem by learning a robust distance function. These methods learn a mapping subspace by forcing the distance of the positive pair much smaller than the negative pair by a strict constraint. The metric model is over-fitting to the training dataset. Due to drastic appearance variations, the handcrafted features are weak of representation for person re-identification. To address these problems, we propose a joint distance measure based approach, which learns a Mahalanobis distance and a Euclidean distance with a novel feature jointly. The novel feature is represented with a dictionary representation based method which considers pedestrian images of different camera views with the same dictionary. The joint distance combine the Mahalanobis distance based on metric learning method with the Euclidean distance based on the novel feature to measure the similarity between matching pairs. Extensive experiments are conducted on the publicly available bench marking datasets VIPeR and CUHK01. The identification results show that the proposed method reaches a good performance than the comparison methods.

APA, Harvard, Vancouver, ISO, and other styles

25

Li, Boren, and Tomonari Furukawa. "DRM-Based Colour Photometric Stereo Using Diffuse-Specular Separation for Non-Lambertian Surfaces." Journal of Imaging 8, no. 2 (February 8, 2022): 40. http://dx.doi.org/10.3390/jimaging8020040.

Full text

Abstract:

This paper presents a photometric stereo (PS) method based on the dichromatic reflectance model (DRM) using colour images. The proposed method estimates surface orientations for surfaces with non-Lambertian reflectance using diffuse-specular separation and contains two steps. The first step, referred to as diffuse-specular separation, initialises surface orientations in a specular invariant colour subspace and further separates the diffuse and specular components in the RGB space. In the second step, the surface orientations are refined by first initialising specular parameters via solving a log-linear regression problem owing to the separation and then fitting the DRM using Levenburg-Marquardt algorithm. Since reliable information from diffuse reflection free from specularities is adopted in the initialisations, the proposed method is robust and feasible with less observations. At pixels where dense non-Lambertian reflectances appear, signals from specularities are exploited to refine the surface orientations and the additionally acquired specular parameters are potentially valuable for more applications, such as digital relighting. The effectiveness of the newly proposed surface normal refinement step was evaluated and the accuracy in estimating surface orientations was enhanced around 30% on average by including this step. The proposed method was also proven effective in an experiment using synthetic input images comprised of twenty-four different reflectances of dielectric materals. A comparison with nine other PS methods on five representative datasets further prove the validity of the proposed method.

APA, Harvard, Vancouver, ISO, and other styles

26

Kim, Jaehun. "Increasing trust in complex machine learning systems." ACM SIGIR Forum 55, no. 1 (June 2021): 1–3. http://dx.doi.org/10.1145/3476415.3476435.

Full text

Abstract:

Machine learning (ML) has become a core technology for many real-world applications. Modern ML models are applied to unprecedentedly complex and difficult challenges, including very large and subjective problems. For instance, applications towards multimedia understanding have been advanced substantially. Here, it is already prevalent that cultural/artistic objects such as music and videos are analyzed and served to users according to their preference, enabled through ML techniques. One of the most recent breakthroughs in ML is Deep Learning (DL), which has been immensely adopted to tackle such complex problems. DL allows for higher learning capacity, making end-to-end learning possible, which reduces the need for substantial engineering effort, while achieving high effectiveness. At the same time, this also makes DL models more complex than conventional ML models. Reports in several domains indicate that such more complex ML models may have potentially critical hidden problems: various biases embedded in the training data can emerge in the prediction, extremely sensitive models can make unaccountable mistakes. Furthermore, the black-box nature of the DL models hinders the interpretation of the mechanisms behind them. Such unexpected drawbacks result in a significant impact on the trustworthiness of the systems in which the ML models are equipped as the core apparatus. In this thesis, a series of studies investigates aspects of trustworthiness for complex ML applications, namely the reliability and explainability. Specifically, we focus on music as the primary domain of interest, considering its complexity and subjectivity. Due to this nature of music, ML models for music are necessarily complex for achieving meaningful effectiveness. As such, the reliability and explainability of music ML models are crucial in the field. The first main chapter of the thesis investigates the transferability of the neural network in the Music Information Retrieval (MIR) context. Transfer learning, where the pre-trained ML models are used as off-the-shelf modules for the task at hand, has become one of the major ML practices. It is helpful since a substantial amount of the information is already encoded in the pre-trained models, which allows the model to achieve high effectiveness even when the amount of the dataset for the current task is scarce. However, this may not always be true if the "source" task which pre-trained the model shares little commonality with the "target" task at hand. An experiment including multiple "source" tasks and "target" tasks was conducted to examine the conditions which have a positive effect on the transferability. The result of the experiment suggests that the number of source tasks is a major factor of transferability. Simultaneously, it is less evident that there is a single source task that is universally effective on multiple target tasks. Overall, we conclude that considering multiple pre-trained models or pre-training a model employing heterogeneous source tasks can increase the chance for successful transfer learning. The second major work investigates the robustness of the DL models in the transfer learning context. The hypothesis is that the DL models can be susceptible to imperceptible noise on the input. This may drastically shift the analysis of similarity among inputs, which is undesirable for tasks such as information retrieval. Several DL models pre-trained in MIR tasks are examined for a set of plausible perturbations in a real-world setup. Based on a proposed sensitivity measure, the experimental results indicate that all the DL models were substantially vulnerable to perturbations, compared to a traditional feature encoder. They also suggest that the experimental framework can be used to test the pre-trained DL models for measuring robustness. In the final main chapter, the explainability of black-box ML models is discussed. In particular, the chapter focuses on the evaluation of the explanation derived from model-agnostic explanation methods. With black-box ML models having become common practice, model-agnostic explanation methods have been developed to explain a prediction. However, the evaluation of such explanations is still an open problem. The work introduces an evaluation framework that measures the quality of the explanations employing fidelity and complexity. Fidelity refers to the explained mechanism's coherence to the black-box model, while complexity is the length of the explanation. Throughout the thesis, we gave special attention to the experimental design, such that robust conclusions can be reached. Furthermore, we focused on delivering machine learning framework and evaluation frameworks. This is crucial, as we intend that the experimental design and results will be reusable in general ML practice. As it implies, we also aim our findings to be applicable beyond the music applications such as computer vision or natural language processing. Trustworthiness in ML is not a domain-specific problem. Thus, it is vital for both researchers and practitioners from diverse problem spaces to increase awareness of complex ML systems' trustworthiness. We believe the research reported in this thesis provides meaningful stepping stones towards the trustworthiness of ML.

APA, Harvard, Vancouver, ISO, and other styles

27

Szirmay-Kalos, László, Ágota Kacsó, Milán Magdics, and Balázs Tóth. "Robust compartmental model fitting in direct emission tomography reconstruction." Visual Computer, February 6, 2021. http://dx.doi.org/10.1007/s00371-020-02041-x.

Full text

Abstract:

AbstractDynamic tomography reconstructs a time activity curve (TAC) for every voxel assuming that the algebraic form of the function is known a priori. The algebraic form derived from the analysis of compartmental models depends nonlinearly on the nonnegative parameters to be determined. Direct methods apply fitting in every iteration step. Because of the iterative nature of the maximum likelihood–expectation maximization (ML–EM) reconstruction, the fitting result of the previous step can serve as a good starting point in the current step; thus, after the first iteration we have a guess that is not far from the solution, which allows the use of gradient-based local optimization methods. However, finding good initial guesses for the first ML–EM iteration is a critical problem since gradient-based local optimization algorithms do not guarantee convergence to the global optimum if they are started at an inappropriate location. This paper examines the robust solution of the fitting problem both in the initial phase and during the ML–EM iteration. This solution is implemented on GPUs and is built into the 4D reconstruction module of the TeraTomo software.

APA, Harvard, Vancouver, ISO, and other styles

28

Fan, Aoxiang, Jiayi Ma, Xingyu Jiang, and Haibin Ling. "Efficient Deterministic Search with Robust Loss Functions for Geometric Model Fitting." IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 1. http://dx.doi.org/10.1109/tpami.2021.3109784.

Full text

APA, Harvard, Vancouver, ISO, and other styles

29

Zhang, Jing, Yuchao Dai, Tong Zhang, Mehrtash T. Harandi, Nick Barnes, and Richard Hartley. "Learning Saliency from Single Noisy Labelling: A Robust Model Fitting Perspective." IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 1. http://dx.doi.org/10.1109/tpami.2020.3046486.

Full text

APA, Harvard, Vancouver, ISO, and other styles

30

Shen, Li-Yong, Meng-Xing Wang, Hong-Yu Ma, Yi-Fei Feng, and Chun-Ming Yuan. "A framework from point clouds to workpieces." Visual Computing for Industry, Biomedicine, and Art 5, no. 1 (August 23, 2022). http://dx.doi.org/10.1186/s42492-022-00117-0.

Full text

Abstract:

AbstractCombining computer-aided design and computer numerical control (CNC) with global technical connections have become interesting topics in the manufacturing industry. A framework was implemented that includes point clouds to workpieces and consists of a mesh generation from geometric data, optimal surface segmentation for CNC, and tool path planning with a certified scallop height. The latest methods were introduced into the mesh generation with implicit geometric regularization and total generalized variation. Once the mesh model was obtained, a fast and robust optimal surface segmentation method is provided by establishing a weighted graph and searching for the minimum spanning tree of the graph for extraordinary points. This method is easy to implement, and the number of segmented patches can be controlled while preserving the sharp features of the workpiece. Finally, a contour parallel tool-path with a confined scallop height is generated on each patch based on B-spline fitting. Experimental results show that the proposed framework is effective and robust.

APA, Harvard, Vancouver, ISO, and other styles

31

Samal, Sidharth, and Rajashree Dash. "A TOPSIS-ELM framework for stock index price movement prediction." Intelligent Decision Technologies, May 21, 2021, 1–19. http://dx.doi.org/10.3233/idt-200013.

Full text

Abstract:

In recent years Extreme Learning Machine (ELM) has gained the interest of various researchers due to its superior generalization and approximation capability. The network architecture and type of activation functions are the two important factors that influence the performance of an ELM. Hence in this study, a Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) oriented multi-criteria decision making (MCDM) framework is suggested for analyzing various ELM models developed with distinct activation functions with respect to sixteen evaluation criteria. Evaluating the performance of the ELM with respect to multiple criteria instead of single criterion can help in designing a more robust network. The proposed framework is used as a binary classification system for pursuing the problem of stock index price movement prediction. The model is empirically evaluated by using historical data of three stock indices such as BSE SENSEX, S&P 500 and NIFTY 50. The empirical study has disclosed promising results by evaluating ELM with different activation functions as well as multiple criteria.

APA, Harvard, Vancouver, ISO, and other styles

32

Yechuri, Sivaramakrishna, and Sunny Dayal Vanabathina. "Genetic Algorithm-Based Adaptive Wiener Gain for Speech Enhancement Using an Iterative Posterior NMF." International Journal of Image and Graphics, October 3, 2022. http://dx.doi.org/10.1142/s0219467823500547.

Full text

Abstract:

In this paper, we propose a genetic algorithm-based adaptive Wiener gain for speech enhancement using an iterative posterior non-negative matrix factorization (NMF). In the recent past, NMF-based Wiener filtering methods were used to improve the performance of speech enhancement, which has shown that they provide better performance when compared with conventional NMF methods. But performance degrades in non-stationary noise environments. Template-based approaches are more robust and perform better in non-stationary noise environments compared to statistical model-based approaches but are dependent on a priori information. Combining the approaches avoids the drawbacks of both. To improve the performance further, speech and noise bases are adapted simultaneously in the NMF approach. The usage of Super-Gaussian constraints in iterative NMF still improves the performance in non-stationary noise. The silence frame is a challenging task in the case of NMF; still there will be some amount of noise present in those frames. For further enhancement, we have combined with a genetic algorithm (GA)-based adaptive Wiener filter which performs well in denoising and also the GA search the adaptive [Formula: see text] allows us to control the trade-off between fitting the observed spectrogram of mixed speech and noise achieving high likelihood under our prior model. The proposed method outperforms other benchmark algorithms in terms of the source to distortion ratio (SDR), short-time objective intelligibility (STOI), and perceptual evaluation of speech quality (PESQ).

APA, Harvard, Vancouver, ISO, and other styles

Journal articles on the topic 'Computer vision; robust model fitting; preference'

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles