Gotowa bibliografia na temat „Lowlight Restored Image Quality”
Utwórz poprawne odniesienie w stylach APA, MLA, Chicago, Harvard i wielu innych
Zobacz listy aktualnych artykułów, książek, rozpraw, streszczeń i innych źródeł naukowych na temat „Lowlight Restored Image Quality”.
Przycisk „Dodaj do bibliografii” jest dostępny obok każdej pracy w bibliografii. Użyj go – a my automatycznie utworzymy odniesienie bibliograficzne do wybranej pracy w stylu cytowania, którego potrzebujesz: APA, MLA, Harvard, Chicago, Vancouver itp.
Możesz również pobrać pełny tekst publikacji naukowej w formacie „.pdf” i przeczytać adnotację do pracy online, jeśli odpowiednie parametry są dostępne w metadanych.
Artykuły w czasopismach na temat "Lowlight Restored Image Quality"
1
Refhiansyah, Anggie Irfhan, Didi Suhaedi i Yurika Permanasari. "Penggunaan Topsis untuk Menentukan Exposure Terbaik pada Kamera yang Memiliki Sensor M4/3". Bandung Conference Series: Mathematics 1, nr 1 (7.12.2021): 1–6. http://dx.doi.org/10.29313/bcsm.v1i1.12.
Pełny tekst źródłaStreszczenie:
Abstract. Cameras that have small sensors such as Micro Four Thirds (M4/3) are experiencing increasing interest in the market today, this is due to the small and compact size of the camera. However, the weakness of cameras with small sensors is that the quality is not as good as those of cameras with larger sensors, especially in lowlight situations because the electronic noise (noise) increases at high ISOs, making it quite difficult to determine the best exposure in these situations. The Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method is used to select the best exposure conditions with the aim of ranking each alternative to be compared, with criteria including shutter speed, aperture and ISO. The result of this research is the total preference value of all criteria. The highest value states that these conditions are ideal for taking pictures in lowlight conditions. Validation is done by looking at the results of the histogram of the image, which shows the quality of the image is good or not.
Abstrak. Kamera yang memiliki sensor kecil seperti Micro Four Thirds (M4/3) mengalami peningkatan peminat di pasaran saat ini, hal tersebut di karenakan ukuran kameranya yang kecil dan kompak. Tetapi, kelemahan kamera dengan sensor yang kecil adalah kualitasnya yang tidak sebaik kamera dengan sensor yang lebih besar, terutama pada situasi lowlight karena gangguan elektroniknya (noise) meningkat pada ISO yang tinggi sehingga cukup sulit untuk menentukan exposure terbaik pada situasi tersebut. Metode Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) digunakan untuk memilih kondisi exposure terbaik dengan tujuan melakukan perankingan dari setiap alternatif yang akan dibandingkan, dengan kriterianya antara lain shutter speed, aperture dan ISO. Hasil dari penelitian ini berupa nilai preferensi total dari semua kriteria. Nilai tertinggi menyatakan bahwa kondisi tersebut ideal dalam mengambil gambar pada kondisi lowlight. Validasi dilakukan dengan melihat hasil histogram citra, yang menunjukkan kualitas dari citra tersebut baik atau tidak.
2
Nhu. "PARAMETRIC BLIND-DECONVOLUTION METHOD TO REMOVE IMAGE ARTIFACTS IN WAVEFRONT CODING IMAGING SYSTEMS". Journal of Military Science and Technology, nr 72A (10.05.2021): 62–68. http://dx.doi.org/10.54939/1859-1043.j.mst.72a.2021.62-68.
Pełny tekst źródłaStreszczenie:
Wavefront coding technique includes a phase mask of asymmetric phase mask kind in the pupil plane to extend the depth of field of an imaging system and the digital processing step to obtain the restored final high-quality image. However, the main drawback of wavefront coding technique is image artifacts on the restored final images. In this paper, we proposed a parameter blind-deconvolution method based on maximizing of the variance of the histogram of restored final images that enables to obtain the restored final image with artifact-free over a large range of defocus.
3
Sun, Guoxin, Xiong Yan, Huizhe Wang, Fei Li, Rui Yang, Jing Xu, Xin Liu, Xiaomao Li i Xiao Zou. "Color restoration based on digital pathology image". PLOS ONE 18, nr 6 (28.06.2023): e0287704. http://dx.doi.org/10.1371/journal.pone.0287704.
Pełny tekst źródłaStreszczenie:
Objective Protective color restoration of faded digital pathology images based on color transfer algorithm. Methods Twenty fresh tissue samples of invasive breast cancer from the pathology department of Qingdao Central Hospital in 2021 were screened. After HE staining, HE stained sections were irradiated with sunlight to simulate natural fading, and every 7 days was a fading cycle, and a total of 8 cycles were experienced. At the end of each cycle, the sections were digitally scanned to retain clear images, and the color changes of the sections during the fading process were recorded. The color transfer algorithm was applied to restore the color of the faded images; Adobe Lightroom Classic software presented the histogram of the image color distribution; UNet++ cell recognition segmentation model was used to identify the color restored images; Natural Image Quality Evaluator (NIQE), Information Entropy (Entropy), and Average Gradient (AG) were applied to evaluate the quality of the restored images. Results The restored image color met the diagnostic needs of pathologists. Compared with the faded images, the NIQE value decreased (P<0.05), Entropy value increased (P<0.01), and AG value increased (P<0.01). The cell recognition rate of the restored image was significantly improved. Conclusion The color transfer algorithm can effectively repair faded pathology images, restore the color contrast between nucleus and cytoplasm, improve the image quality, meet the diagnostic needs and improve the cell recognition rate of the deep learning model.
4
Zhang, Hua, Yi Kai Shi, Kui Dong Huang i Qing Chao Yu. "Image Restoration Method Based on Pre-Filtering for Cone-Beam Computed Tomography". Applied Mechanics and Materials 229-231 (listopad 2012): 1858–61. http://dx.doi.org/10.4028/www.scientific.net/amm.229-231.1858.
Pełny tekst źródłaStreszczenie:
For the problem of image quality degradation of cone-beam Computed Tomography (CBCT) based on flat panel detector (FPD), a constrained least squares iteration (CLSI) restoration method based on pre-filtering is proposed. Firstly, the original projected images are denoised with bilateral filtering algorithm. Then, the denoised projected images are restored with CLSI. Finally, the final restored images are obtained by adding the noise images, which got by subtracting the projected images before and after denoising, to the restored images. The experimental results show that the method well inhibits the noise amplification phenomenon in image restoration, and increases the edge sharpness and contrast-to-noise ratio (CNR) of the projected images and slice images. The CBCT image quality is significantly improved with this method.
5
Xie, Wang i Li. "A Fragile Watermark Scheme for Image Recovery Based on Singular Value Decomposition, Edge Detection and Median Filter". Applied Sciences 9, nr 15 (26.07.2019): 3020. http://dx.doi.org/10.3390/app9153020.
Pełny tekst źródłaStreszczenie:
Many fragile watermark methods have been proposed for image recovery and their performance has been greatly improved. However, jagged edges and confusion still exist in the restored areas and these problems need to be solved to achieve a better visual effect. In this paper, a method for improving recovery quality is proposed that adopts singular value decomposition (SVD) and edge detection for tamper detection and then uses a median filter for image recovery. Variable watermark information can be generated that corresponds to block classifications. With mapping and neighborhood adjustment, the area that has been tampered can be correctly detected. Subsequently, we adopt a filtering operation for the restored image obtained after the inverse watermark embedding process. During the filtering operation, a median filter is used to smooth and remove noise, followed by minimum, maximum and threshold operations to balance the image intensity. Finally, the corresponding pixels of the restored image are replaced with the filtered results. The experimental results of six different tampering attacks conducted on eight test images show that tamper detection method with the edge detection can identify the tampered region correctly but has a higher false alarm rate than other methods. In addition, compared with the other three similar methods previously, using a median filter during image recovery not only improves the visual effect of the restored image but also enhances its quality objectively under most tampering attack conditions.
6
Irshad, Muhammad, Camilo Sanchez-Ferreira, Sana Alamgeer, Carlos H. Llanos i Mylène C. Q. Farias. "No-reference Image Quality Assessment of Underwater Images Using Multi-Scale Salient Local Binary Patterns". Electronic Imaging 2021, nr 9 (18.01.2021): 265–1. http://dx.doi.org/10.2352/issn.2470-1173.2021.9.iqsp-265.
Pełny tekst źródłaStreszczenie:
Images acquired in underwater scenarios may contain severe distortions due to light absorption and scattering, color distortion, poor visibility, and contrast reduction. Because of these degradations, researchers have proposed several algorithms to restore or enhance underwater images. One way to assess these algorithms’ performance is to measure the quality of the restored/enhanced underwater images. Unfortunately, since reference (pristine) images are often not available, designing no-reference (blind) image quality metrics for this type of scenario is still a challenge. In fact, although the area of image quality has evolved a lot in the last decades, estimating the quality of enhanced and restored images is still an open problem. In this work, we present a no-reference image quality evaluation metric for enhanced underwater images (NR-UWIQA) that uses an adapted version of the multi-scale salient local binary pattern operator to extract image features and a machine learning approach to predict quality. The proposed metric was tested on the UID-LEIA database and presented good accuracy performance when compared to other state-of-the-art methods. In summary, the proposed NR-UWQIA method can be used to evaluate the results of restoration techniques quickly and efficiently, opening a new perspective in the area of underwater image restoration and quality assessment.
7
Rezgui, Hicham, Messaoud Maouni, Mohammed Lakhdar Hadji i Ghassen Touil. "Three robust edges stopping functions for image denoising". Boletim da Sociedade Paranaense de Matemática 40 (20.01.2022): 1–12. http://dx.doi.org/10.5269/bspm.45945.
Pełny tekst źródłaStreszczenie:
In this paper, we present three strong edge stopping functions for image enhancement. These edge stopping functions have the advantage of effectively removing the image noise while preserving the true edges and other important features. The obtained results show an improved quality for the restored images compared to existing restoration models.
8
Shemiakina, Julia, Elena Limonova, Natalya Skoryukina, Vladimir V. Arlazarov i Dmitry P. Nikolaev. "A Method of Image Quality Assessment for Text Recognition on Camera-Captured and Projectively Distorted Documents". Mathematics 9, nr 17 (3.09.2021): 2155. http://dx.doi.org/10.3390/math9172155.
Pełny tekst źródłaStreszczenie:
In this paper, we consider the problem of identity document recognition in images captured with a mobile device camera. A high level of projective distortion leads to poor quality of the restored text images and, hence, to unreliable recognition results. We propose a novel, theoretically based method for estimating the projective distortion level at a restored image point. On this basis, we suggest a new method of binary quality estimation of projectively restored field images. The method analyzes the projective homography only and does not depend on the image size. The text font and height of an evaluated field are assumed to be predefined in the document template. This information is used to estimate the maximum level of distortion acceptable for recognition. The method was tested on a dataset of synthetically distorted field images. Synthetic images were created based on document template images from the publicly available dataset MIDV-2019. In the experiments, the method shows stable predictive values for different strings of one font and height. When used as a pre-recognition rejection method, it demonstrates a positive predictive value of 86.7% and a negative predictive value of 64.1% on the synthetic dataset. A comparison with other geometric quality assessment methods shows the superiority of our approach.
9
Wang, Huai Sheng. "A No Interference Optical Image Encryption by a Fresnel Diffraction and a Fourier Transformation". Advanced Materials Research 459 (styczeń 2012): 461–64. http://dx.doi.org/10.4028/www.scientific.net/amr.459.461.
Pełny tekst źródłaStreszczenie:
A no interference optical image encryption is put forward in this paper. The encrypting process is composed of a Fresnel diffraction and a Fourier transformation. A digital image coded with a random phase plate first takes a Fresnel diffraction. The diffraction function is enlarged and coded with another random phase mask. At last the enlarged function undergoes a Fourier transformation. The real part of the transformed function is defined as an encrypted image. In decrypting process, first the encrypted image takes an inverse Fourier transformation. Then the upper left corner of the transformed function is intercepted. According to the space inversion of the transformed function, if the intercepted function takes an inverse Fresnel diffraction, the original digital image can be restored from the final diffraction function. Because there is no interference process in encryption and decryption, the optical system is relatively simple and the quality of restored image is very good
10
Wieslander, Håkan, Carolina Wählby i Ida-Maria Sintorn. "TEM image restoration from fast image streams". PLOS ONE 16, nr 2 (1.02.2021): e0246336. http://dx.doi.org/10.1371/journal.pone.0246336.
Pełny tekst źródłaStreszczenie:
Microscopy imaging experiments generate vast amounts of data, and there is a high demand for smart acquisition and analysis methods. This is especially true for transmission electron microscopy (TEM) where terabytes of data are produced if imaging a full sample at high resolution, and analysis can take several hours. One way to tackle this issue is to collect a continuous stream of low resolution images whilst moving the sample under the microscope, and thereafter use this data to find the parts of the sample deemed most valuable for high-resolution imaging. However, such image streams are degraded by both motion blur and noise. Building on deep learning based approaches developed for deblurring videos of natural scenes we explore the opportunities and limitations of deblurring and denoising images captured from a fast image stream collected by a TEM microscope. We start from existing neural network architectures and make adjustments of convolution blocks and loss functions to better fit TEM data. We present deblurring results on two real datasets of images of kidney tissue and a calibration grid. Both datasets consist of low quality images from a fast image stream captured by moving the sample under the microscope, and the corresponding high quality images of the same region, captured after stopping the movement at each position to let all motion settle. We also explore the generalizability and overfitting on real and synthetically generated data. The quality of the restored images, evaluated both quantitatively and visually, show that using deep learning for image restoration of TEM live image streams has great potential but also comes with some limitations.
Rozprawy doktorskie na temat "Lowlight Restored Image Quality"
1
Sogabe, Maina. "Restored interlaced volumetric imaging increases image quality and scanning speed during intravital imaging in living mice". Kyoto University, 2020. http://hdl.handle.net/2433/253212.
Pełny tekst źródła
2
Kannan, Vignesh. "Perceptual Quality Assessment of Lowlight Restored and Authentically Distorted Images". Thesis, 2022. https://etd.iisc.ac.in/handle/2005/5792.
Pełny tekst źródłaStreszczenie:
The capability of hand-held devices to acquire high-definition visual content has led to a tremendous increase in the number of images and videos captured daily. However, camera hardware and pipelines are not perfect and lead to multiple distortions in the captured content. This makes quality assessment (QA) imperative to advance the qualitative capability of different devices and the pipelines used. More particularly, the aim of perceptual quality assessment is to quantitatively analyze the perceptual quality of the captured content with respect to the distortions observed by the human visual system. This thesis focuses on two aspects of perceptual quality assessment. Firstly, we focus on the subjective and objective quality assessment of low-light restored images. Then we consider the problem of unsupervised quality assessment methods for authentically distorted images.
The quality assessment of restored low-light images is an important tool for benchmarking and improving low-light restoration (LLR) algorithms. While several LLR algorithms exist, the subjective perception of the restored images has been much less studied. Challenges in capturing aligned low-light and well-lit image pairs and collecting a large number of human opinion scores of quality for training warrant the design of unsupervised (or opinion unaware) no-reference (NR) QA methods. In this part, we study the subjective perception of low-light restored images and their unsupervised NR QA. Our contributions are two-fold. We first create a dataset of restored low-light images using various LLR methods, conduct a subjective QA study, and benchmark the performance of existing QA methods. The lack of good perceptual quality metrics designed explicitly for the low-light scenario is an important limitation in advancing the design of restoration methods. To tackle this, we present a self-supervised contrastive learning technique to extract distortion-aware features from the restored low-light images. We show that these features can be effectively used to build an opinion unaware image quality analyzer. Detailed experiments reveal that our unsupervised NR QA model achieves state-of-the-art performance among all such quality measures for low-light restored images.
The quality assessment of camera captured authentically distorted images is challenging due to the lack of a reference. While there is a plethora of supervised no reference image QA algorithms, there is a need to study unsupervised or opinion unaware algorithms based on their superior generalization performance. We explore self-supervised learning (SSL) for the feature design on authentically distorted images to predict quality without training on human labels. While SSL on synthetic distortions has recently shown promise, there is a need to enrich the feature learning on authentic distortions. We propose a novel two-stage learning approach on synthetic and authentically distorted images with different learning methodologies. We perform contrastive learning with positives and negatives that vary with quality on synthetic data to capture quality features. While learning on authentically distorted images, we only consider positives due to the difficulty in obtaining negatives that vary in quality alone. We employ the SimSiam framework to enrich features by fine-tuning on authentically distorted images. We show that the self-supervised features we learn can be used to make perceptually consistent image quality predictions on authentically distorted images without training on any human opinion scores. We achieve state-of-the-art performance on multiple authentically distorted datasets without training on them.
Części książek na temat "Lowlight Restored Image Quality"
1
Sabelkin, Mike, i François Gagnon. "Data Transmission Oriented on the Object, Communication Media, Application, and State of Communication Systems". W Advancements and Innovations in Wireless Communications and Network Technologies, 117–32. IGI Global, 2013. http://dx.doi.org/10.4018/978-1-4666-2154-1.ch009.
Pełny tekst źródłaStreszczenie:
The proposed communication system architecture is called TOMAS, which stands for data Transmission oriented on the Object, communication Media, Application, and state of communication Systems. TOMAS could be considered a Cross-Layer Interface (CLI) proposal, since it refers to multiple layers of the Open Systems Interconnection Basic Reference Model (OSI). Given particular scenarios of image transmission over a wireless LOS channel, the wireless TOMAS system demonstrates superior performance compared to a JPEG2000+OFDM system in restored image quality parameters over a wide range of wireless channel parameters. A wireless TOMAS system provides progressive lossless image transmission under influence of moderate fading without any kind of channel coding and estimation. The TOMAS system employs a patent pending fast analysis/synthesis algorithm, which does not use any multiplications, and it uses three times less real additions than the one of JPEG2000+OFDM.
2
R., Vishalakshi G., Gopala Krishna i Hanumantha Raju. "Wavelet Energy-Based Adaptive Retinex Algorithm for Low Light Mobile Video Enhancement". W Advances in Systems Analysis, Software Engineering, and High Performance Computing, 16–39. IGI Global, 2023. http://dx.doi.org/10.4018/978-1-6684-7524-9.ch002.
Pełny tekst źródłaStreszczenie:
In today's world, smartphones are ubiquitous and feature high-quality cameras and video recording capabilities. The camera shake, shadows, or other environmental factors lead to poor video, even in low-lighting situations with a high-end camera. To preserve and enhance low-light mobile video, a wavelet energy-based adaptive retinex algorithm is proposed. The first step in the method is to extract frames from the composite video before it is fed into the algorithm in HSV space. The authors then apply the wavelet energy-based adaptive retinex algorithm to the dynamic range-extended value channel. Lighting conditions that cause video degradation are restored adaptively to their natural brightness. A color restoration technique that improves the conventional retinex method fixes the gray world violation problem. Wavelet energy is used as a metric in concurrence with the retinex algorithm to objectively validate image enhancement quality. An experimental work of more than 300 still images and videos show that the proposed technique outperforms the current state of the art.
3
Christensen, Thomas C. "Confessions of a film restorer". W The Translation of Films, 1900-1950, 101–10. British Academy, 2019. http://dx.doi.org/10.5871/bacad/9780197266434.003.0006.
Pełny tekst źródłaStreszczenie:
When restoring a film, the aim is naturally always to provide the definitive version. However, many factors make this an impossible mission. This chapter draws on actual film archival practice and theory, exposing a minefield of obstacles facing any academic study trying to examine film history based on restored works. The focus is on silent cinema restoration, intertitles, and translation issues. Using Mark-Paul Meyer and Paul Read’s categories—from a one-to-one duplication to the creation of an altogether new work—the aim is to give an insight into the complexity of silent film restoration and the practical, and sometimes very unacademic, nature of the actual restoration work. The fact that most film restorations typically concentrate on image quality rather than titles, which are often merely supposed to support the visual action, adds to the complexity of transparency about the provenance of the filmic titles as an object of study.
Streszczenia konferencji na temat "Lowlight Restored Image Quality"
1
Yongjuan Pan i Jin Wang. "Embedded lowlight image quality measure". W 2012 IEEE 3rd International Conference on Software Engineering and Service Science (ICSESS). IEEE, 2012. http://dx.doi.org/10.1109/icsess.2012.6269463.
Pełny tekst źródła
2
Lei, Yin, Di Xiaoguang, Fu Shaowen, Gao Lei i Ma Jie. "Image blind restoration based on blur identification and quality assessment of restored image". W 2015 34th Chinese Control Conference (CCC). IEEE, 2015. http://dx.doi.org/10.1109/chicc.2015.7260364.
Pełny tekst źródła
3
Yang, Shiduo, Fayez Al-Mutairi, Tianhua Zhang, Alexis He, Chandramani Shrivastava, Yen Han Shim i Ihsan Taufik Pasaribu. "An Innovated Image-Based Approach for Logging-While-Drilling Image Quality Improvement in Stick and Slip Phase". W IADC/SPE Asia Pacific Drilling Technology Conference and Exhibition. SPE, 2022. http://dx.doi.org/10.2118/209913-ms.
Pełny tekst źródłaStreszczenie:
Abstract Stick/slip motion is an extremely severe torsional oscillation that can cause the drill bit to come to a complete stop and then followed by an extra acceleration of the surface rotation. Due to the lack of downhole sensors for direct speed measurement of logging-while-drilling (LWD) image tools, the depth measured on the surface can appear to be smoother than the downhole sensors’ real movement. Using the smoothed surface depth for time-to-depth gating of the images might lead to the formation features appearing to be compressed or stretched semicyclically in the depth domain when sensor stick/slip occurs. In this paper, an innovated approach is presented to restore image features altered by the depth desynchronization and stick/slip issue. This method initially identified the drilling status from the interpolated surface depth in a time domain, including sensor movement direction; i.e.,drilling down or reaming down, tool stop, and connection breakdown time. In parallel, the drilling statuses were also identified from a downhole image feature similarity and the artificial intelligence (AI)-aided functions. The surface depth can be synchronized to downhole image measurements in the time domain based on the identified drilling statuses. In the end, the stick/slip time intervals were identified from the synchronized depth when the depth variation exceeded the image's vertical resolution, and the pseudovelocity was filtered and computed in the time domain. The stick/slip image features were restored in the depth domain efficiently after time-to-depth gating using the new processed depth. This new approach will be applied to an LWD ultrasonic image obtained from a Middle East carbonate reservoir. The drilling statuses were identified confidently in the time domain and no additional stick/slip features were found in the image data in the depth domain. The processed images revealed the reservoir heterogeneity with clear vug features, additional bedding boundary, and confident fracture features. In a severe stick/slip mode, the LWD resistivity image was processed with downhole speed correction from the multiple sensors’ signal, but the block image features remained on the image in the depth domain. The image features were restored efficiently with an adapted solution from this innovative approach.
4
Jeon, Hyung Wook, Yim Kul Lee i Jung Young Son. "Effects of system parameters on image transmission through fiber using self-pumped phase conjugation". W OSA Annual Meeting. Washington, D.C.: Optica Publishing Group, 1992. http://dx.doi.org/10.1364/oam.1992.turr3.
Pełny tekst źródłaStreszczenie:
Optical fiber image transmission using a barium titanate crystal for self-pumped phase conjugation is presented.1 An input object, the letter "K," illuminated by a collimated argon-ion laser beam (514.5 nm), is focused into a multimode fiber (50 μm core and step index mode) and then phase conjugated in the crystal. The phase conjugated image retraverses the same fiber to compensate for the modal dispersion of the fiber. For a given experimental setup, an optimum image quality was obtained qualitatively at f = 75.6 mm in the range of 60 mm to 200 mm. As f increased, the restored K was gradually de graded in quality and significantly deformed in shape, particularly at f = 200 mm. As f decreased (e.g., f = 60 mm), the character K became quite noisy at f = 60 mm because of the increase in high spatial frequency components contained in the restored image, and the size of speckles on the restored background was reduced. Increasing the illuminating beam intensity also caused the restored K to be deformed and blurred as the intensity was varied from 10 mW to 400 mW. A reasonably good result was obtained for a wide range of the beam intensity (e.g., from 100 to 300 mW) at f = 75.6 mm, while increasing or decreasing the intensity from 200 mW significantly deformed the letter K, particularly at f = 150 mm. No restoration of the input K was obtained for f = 200 mm at high power (e.g., 400 mW). Both qualitative and quantitative analysis will be presented under various experimental conditions.
5
Leng, Zhiying, i Zhentao Wang. "An Image Quality Improvement Method Based on Neural Network for Digital Radiography Security Inspection System". W 2020 International Conference on Nuclear Engineering collocated with the ASME 2020 Power Conference. American Society of Mechanical Engineers, 2020. http://dx.doi.org/10.1115/icone2020-16344.
Pełny tekst źródłaStreszczenie:
Abstract As an essential method for security inspection in nuclear facilities, digital radiography has the ability to find hidden contraband efficiently. However, the images obtained by current scanning digital radiography system can be degraded by several factors, such as statistical noise and response time of detectors. At high scanning speed, the statistical noise and vibration of the system deteriorates the quality of images. In addition, the reduction of image quality will influence the accuracy of image observation and recognition. To meet the demand of detection efficiency and quality, it is necessary to guarantee the quality of images under high scanning speed. Thus, to improve image quality of vehicles’ digital radiography at a certain scanning speed, we proposed an approach (VDR-CNN) to reduce or eliminate image noise, which is a convolutional neural network (CNN) with residual learning. The high-quality images obtained at low scanning speed of system served as the ground-truth image for VDR-CNN, while the low-quality counterpart corresponding to the high scanning speed served as the input. Then, the two images mentioned above constitute a training pair. By training this network with a set of training pairs, the mapping function of promoting image quality will be automatically learned so that the restored image can be obtained from the low-quality counterpart through the trained VDR-CNN. Moreover, this method avoids the difficulty in figuring and analyzing the complicated image degradation model. A series of experiments was carried out through the 60Co inspection system developed by Institute of Nuclear and New Energy Technology, Tsinghua University. The experimental result shows that this method has attained a satisfying result in denoising and preserving details of images and outperforms BM3D algorithm in terms of both image quality improvement and the processing speed. In conclusion, the proposed method improves the image quality of vehicles’ digital radiography and it is proved better than traditional methods.
6
Ye, Hang, Chi Zhou i Wenyao Xu. "Image Based Slicing and Tool Path Planning for Hybrid Stereolithography Additive Manufacturing". W ASME 2016 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. American Society of Mechanical Engineers, 2016. http://dx.doi.org/10.1115/detc2016-60245.
Pełny tekst źródłaStreszczenie:
Hybrid stereolithograpgy (SLA) process synthesizes the laser scanning based SLA system and mask projection based SLA system. It adopts laser as the energy source for scanning the border of a 2D pattern, whereas a mask image is used to solidify the interior area. By integrating the merits of the two subsystems, the hybrid SLA process can achieve relatively high surface quality without sacrificing the productivity. For the hybrid system, closed polygon contours are required to direct laser scanning, and a binary image is also needed for mask projection. We proposed a novel image based slicing method. This method can convert the 3D model into a series of binary images directly, and each image is corresponding to the cross-session of the model at a specific height. Based on the resultant binary image, we use image processing method to gradually shrink the image. The contours of shrunk image are traced and then restored as polygons to direct the laser spot movement. The final shrunk image will serve as the input for mask projection. The experimental result of several test cases demonstrate that proposed method is substantially more time-efficient than traditional approaches.
7
Qidwai, Uvais, i Chi-Hau Chen. "Blind Image Restoration for Ultrasonic C-Scan Using Constrained 4th Order Cumulants". W ASME 2001 International Mechanical Engineering Congress and Exposition. American Society of Mechanical Engineers, 2001. http://dx.doi.org/10.1115/imece2001/nde-25812.
Pełny tekst źródłaStreszczenie:
Abstract C-Scans are ways to visualize the sample under study by utilizing the reflections from various levels of non-homogenous wave transfer within the sample. Unlike other imaging techniques, C-scan are usually constructed from the pulse-echoed A-Scans by mapping the 1D windowed signal into a point corresponding to a pixel on the C-scan by calculating its energy within the window. Hence, although the A-scans are predominantly Gaussian in nature, the spatial 1D waveforms mapping into spatial energy values, results in completely unpredictable statistical characteristics. Also, the medium characteristics incorporate distortions that are essentially due to a non-minimum phase system response. Hence, the usual Second Order Statistics (SOS) based identification and deconvolution, i.e., correlation and covariance based techniques, may not work very well in this case. In this paper, an approach is presented to use 4th order cumulants to deconvolve the effects of blurring in the C-Scans due to above-mentioned effects. The proposed approach is completely blind to the source or the type of distortion and the formulation is purely two-dimensional. When the blurring function is modeled as an Auto Regressive (AR) process, the image is restored recursively with the application of the inverse filter based on the AR estimate. A significant improvement in the image quality has been demonstrated. Especially, the edges are detected more prominently than present in the original image. Very little or no post processing is needed to obtain the final image.
8
Li, Zelin, Dan Zeng, Xiao Yan, Qiaomu Shen i Bo Tang. "Analyzing and Combating Attribute Bias for Face Restoration". W Thirty-Second International Joint Conference on Artificial Intelligence {IJCAI-23}. California: International Joint Conferences on Artificial Intelligence Organization, 2023. http://dx.doi.org/10.24963/ijcai.2023/128.
Pełny tekst źródłaStreszczenie:
Face restoration (FR) recovers high resolution (HR) faces from low resolution (LR) faces and is challenging due to its ill-posed nature. With years of development, existing methods can produce quality HR faces with realistic details. However, we observe that key facial attributes (e.g., age and gender) of the restored faces could be dramatically different from the LR faces and call this phenomenon attribute bias, which is fatal when using FR for applications such as surveillance and security. Thus, we argue that FR should consider not only image quality as in existing works but also attribute bias. To this end, we thoroughly analyze attribute bias with extensive experiments and find that two major causes are the lack of attribute information in LR faces and bias in the training data. Moreover, we propose the DebiasFR framework to produce HR faces with high image quality and accurate facial attributes. The key design is to explicitly model the facial attributes, which also allows to adjust facial attributes for the output HR faces. Experiment results show that DebiasFR has comparable image quality but significantly smaller attribute bias when compared with state-of-the-art FR methods.
9
Tam, Eddy C., Shudong Wu, Aris Tanone, Francis T. S. Yu i Don A. Gregory. "Closed loop binary phase correction of a LCTV using a point diffraction interferometer". W OSA Annual Meeting. Washington, D.C.: Optica Publishing Group, 1989. http://dx.doi.org/10.1364/oam.1989.tuc3.
Pełny tekst źródłaStreszczenie:
It was pointed out that an inexpensive commercial available liquid crystal TV can be operated as a binary phase-only spatial light modulator by orienting the second analyzer to be perpendicular to the bisector of the two transmitted polarization states of the LCTV.1 Therefore, it is possible to use the device to correct the phase nonuniformity of the device itself, as well as other phase distortion in the optical system. We employ the so-called point diffraction interferometer2 to examine the phase distortion. The interference pattern captured by a CCD camera is then binarized and sent back to the LCTV by using a computer. A ±π phase shift is therefore effectively added to the LCTV to restore the nonuniform phase. It must be mentioned that the system operates in an on-line and closed loop architecture which enables the optimum phase correction mask to be generated. Moreover, the interferometer does not require high quality optical components to produce the interference pattern, and the phase restored system can be immediately utilized in some image processing applications, such as binary phase-only joint transform correlation.
10
Rubin, Gary S., Kathleen Turano i Ronald A. Schuchard. "Effect of contrast stretching and spatial-frequency range on reading rate". W OSA Annual Meeting. Washington, D.C.: Optica Publishing Group, 1988. http://dx.doi.org/10.1364/oam.1988.tuy7.
Pełny tekst źródłaStreszczenie:
Studies of image quality with photographic and TV systems suggest that visual performance depends on the effective contrast of the image (the difference between image contrast and the observer’s contrast threshold integrated across the spatial-frequency spectrum of the image). This implies that an increase in image contrast will compensate for a reduction in spatial-frequency range due to low-pass filtering. To test this hypothesis, we measured reading rates for low-pass filtered text. Letters were digitized to 256 grey levels on a 32- × 32-pixel array and low pass filtered. The filters had cutoff frequencies (at half-amplitude) of 1.34, 1.02, or 0.60 cycles/letter. Paragraphs composed of letters subtending 0.5° were displayed for 20 s on a monochrome monitor with maximum luminance of 120 cd/m2. Observers read the text aloud, and the reading rate (number of words read correctly per minute) was computed. The process of low-pass filtering also reduces the contrast of the text. We compared reading rates for the filtered text with reading rates for filtered text in which the contrast was restored (stretched) to the maximum attainable with our display (0.94). Reading rates for the filtered text decreased with reduced cutoff frequency (down 81 % for the lowest cutoff frequency, 0.60 cycle/letter). However, reading rates for the stretched filtered text were less affected by filtering (down only 20% at 0.60 cycle/letter). The results indicate that the increased image contrast can compensate for a reduction in spatial-frequency range due to low-pass filtering.