The Experts below are selected from a list of 33525 Experts worldwide ranked by ideXlab platform
Michael S. Brown - One of the best experts on this subject based on the ideXlab platform.
-
Learning Raw Image Reconstruction-Aware Deep Image Compressors
IEEE transactions on pattern analysis and machine intelligence, 2019Co-Authors: Abhijith Punnappurath, Michael S. BrownAbstract:Deep learning-based Image compressors are actively being explored in an effort to supersede conventional Image compression algorithms, such as JPEG. Conventional and deep learning-based compression algorithms focus on minimizing Image fidelity errors in the nonlinear standard RGB (sRGB) color space. However, for many computer vision tasks, the sensor's linear Raw-RGB Image is desirable. Recent work has shown that the original Raw-RGB Image can be reconstructed using only small amounts of metadata embedded inside the JPEG Image [1] . However, [1] relied on the conventional JPEG encoding that is unaware of the Raw-RGB reconstruction task. In this paper, we examine the ability of deep Image compressors to be “aware” of the additional objective of Raw reconstruction. Towards this goal, we describe a general framework that enables deep networks targeting Image compression to jointly consider both Image fidelity errors and Raw reconstruction errors. We describe this approach in two scenarios: (1) the network is trained from scratch using our proposed joint loss, and (2) a network originally trained only for sRGB fidelity loss is later fine-tuned to incorporate our Raw reconstruction loss. When compared to sRGB fidelity-only compression, our combined loss leads to appreciable improvements in PSNR of the Raw reconstruction with only minor impact on sRGB fidelity as measured by MS-SSIM.
-
Raw Image Reconstruction Using a Self-contained sRGB–JPEG Image with Small Memory Overhead
International Journal of Computer Vision, 2018Co-Authors: Rang M. H. Nguyen, Michael S. BrownAbstract:Most camera Images are saved as 8-bit standard RGB (sRGB) compressed JPEGs. Even when JPEG compression is set to its highest quality, the encoded sRGB Image has been significantly processed in terms of color and tone manipulation. This makes sRGB–JPEG Images undesirable for many computer vision tasks that assume a direct relationship between pixel values and incoming light. For such applications, the Raw Image format is preferred, as Raw represents a minimally processed, sensor-specific RGB Image that is linear with respect to scene radiance. The dRawback with Raw Images, however, is that they require large amounts of storage and are not well-supported by many imaging applications. To address this issue, we present a method to encode the necessary data within an sRGB–JPEG Image to reconstruct a high-quality Raw Image. Our approach requires no calibration of the camera’s colorimetric properties and can reconstruct the original Raw to within 0.5% error with a small memory overhead for the additional data (e.g., 128 KB). More importantly, our output is a fully self-contained 100% compliant sRGB–JPEG file that can be used as-is, not affecting any existing Image workflow—the Raw Image data can be extracted when needed, or ignored otherwise. We detail our approach and show its effectiveness against competing strategies.
-
Raw Image reconstruction using a self contained srgb jpeg Image with small memory overhead
International Journal of Computer Vision, 2018Co-Authors: Rang M. H. Nguyen, Michael S. BrownAbstract:Most camera Images are saved as 8-bit standard RGB (sRGB) compressed JPEGs. Even when JPEG compression is set to its highest quality, the encoded sRGB Image has been significantly processed in terms of color and tone manipulation. This makes sRGB–JPEG Images undesirable for many computer vision tasks that assume a direct relationship between pixel values and incoming light. For such applications, the Raw Image format is preferred, as Raw represents a minimally processed, sensor-specific RGB Image that is linear with respect to scene radiance. The dRawback with Raw Images, however, is that they require large amounts of storage and are not well-supported by many imaging applications. To address this issue, we present a method to encode the necessary data within an sRGB–JPEG Image to reconstruct a high-quality Raw Image. Our approach requires no calibration of the camera’s colorimetric properties and can reconstruct the original Raw to within 0.5% error with a small memory overhead for the additional data (e.g., 128 KB). More importantly, our output is a fully self-contained 100% compliant sRGB–JPEG file that can be used as-is, not affecting any existing Image workflow—the Raw Image data can be extracted when needed, or ignored otherwise. We detail our approach and show its effectiveness against competing strategies.
-
Raw Image reconstruction using a self contained srgb jpeg Image with only 64 kb overhead
Computer Vision and Pattern Recognition, 2016Co-Authors: Rang M. H. Nguyen, Michael S. BrownAbstract:Most camera Images are saved as 8-bit standard RGB (sRGB) compressed JPEGs. Even when JPEG compression is set to its highest quality, the encoded sRGB Image has been significantly processed in terms of color and tone manipulation. This makes sRGB-JPEG Images undesirable for many computer vision tasks that assume a direct relationship between pixel values and incoming light. For such applications, the Raw Image format is preferred, as Raw represents a minimally processed, sensor-specific RGB Image with higher dynamic range that is linear with respect to scene radiance. The dRawback with Raw Images, however, is that they require large amounts of storage and are not well-supported by many imaging applications. To address this issue, we present a method to encode the necessary metadata within an sRGB Image to reconstruct a high-quality Raw Image. Our approach requires no calibration of the camera and can reconstruct the original Raw to within 0:3% error with only a 64 KB overhead for the additional data. More importantly, our output is a fully selfcontained 100% complainant sRGB-JPEG file that can be used as-is, not affecting any existing Image workflow - the Raw Image can be extracted when needed, or ignored otherwise. We detail our approach and show its effectiveness against competing strategies.
-
CVPR - Raw Image Reconstruction Using a Self-Contained sRGB-JPEG Image with Only 64 KB Overhead
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016Co-Authors: Rang M. H. Nguyen, Michael S. BrownAbstract:Most camera Images are saved as 8-bit standard RGB (sRGB) compressed JPEGs. Even when JPEG compression is set to its highest quality, the encoded sRGB Image has been significantly processed in terms of color and tone manipulation. This makes sRGB-JPEG Images undesirable for many computer vision tasks that assume a direct relationship between pixel values and incoming light. For such applications, the Raw Image format is preferred, as Raw represents a minimally processed, sensor-specific RGB Image with higher dynamic range that is linear with respect to scene radiance. The dRawback with Raw Images, however, is that they require large amounts of storage and are not well-supported by many imaging applications. To address this issue, we present a method to encode the necessary metadata within an sRGB Image to reconstruct a high-quality Raw Image. Our approach requires no calibration of the camera and can reconstruct the original Raw to within 0:3% error with only a 64 KB overhead for the additional data. More importantly, our output is a fully selfcontained 100% complainant sRGB-JPEG file that can be used as-is, not affecting any existing Image workflow - the Raw Image can be extracted when needed, or ignored otherwise. We detail our approach and show its effectiveness against competing strategies.
Rang M. H. Nguyen - One of the best experts on this subject based on the ideXlab platform.
-
Raw Image Reconstruction Using a Self-contained sRGB–JPEG Image with Small Memory Overhead
International Journal of Computer Vision, 2018Co-Authors: Rang M. H. Nguyen, Michael S. BrownAbstract:Most camera Images are saved as 8-bit standard RGB (sRGB) compressed JPEGs. Even when JPEG compression is set to its highest quality, the encoded sRGB Image has been significantly processed in terms of color and tone manipulation. This makes sRGB–JPEG Images undesirable for many computer vision tasks that assume a direct relationship between pixel values and incoming light. For such applications, the Raw Image format is preferred, as Raw represents a minimally processed, sensor-specific RGB Image that is linear with respect to scene radiance. The dRawback with Raw Images, however, is that they require large amounts of storage and are not well-supported by many imaging applications. To address this issue, we present a method to encode the necessary data within an sRGB–JPEG Image to reconstruct a high-quality Raw Image. Our approach requires no calibration of the camera’s colorimetric properties and can reconstruct the original Raw to within 0.5% error with a small memory overhead for the additional data (e.g., 128 KB). More importantly, our output is a fully self-contained 100% compliant sRGB–JPEG file that can be used as-is, not affecting any existing Image workflow—the Raw Image data can be extracted when needed, or ignored otherwise. We detail our approach and show its effectiveness against competing strategies.
-
Raw Image reconstruction using a self contained srgb jpeg Image with small memory overhead
International Journal of Computer Vision, 2018Co-Authors: Rang M. H. Nguyen, Michael S. BrownAbstract:Most camera Images are saved as 8-bit standard RGB (sRGB) compressed JPEGs. Even when JPEG compression is set to its highest quality, the encoded sRGB Image has been significantly processed in terms of color and tone manipulation. This makes sRGB–JPEG Images undesirable for many computer vision tasks that assume a direct relationship between pixel values and incoming light. For such applications, the Raw Image format is preferred, as Raw represents a minimally processed, sensor-specific RGB Image that is linear with respect to scene radiance. The dRawback with Raw Images, however, is that they require large amounts of storage and are not well-supported by many imaging applications. To address this issue, we present a method to encode the necessary data within an sRGB–JPEG Image to reconstruct a high-quality Raw Image. Our approach requires no calibration of the camera’s colorimetric properties and can reconstruct the original Raw to within 0.5% error with a small memory overhead for the additional data (e.g., 128 KB). More importantly, our output is a fully self-contained 100% compliant sRGB–JPEG file that can be used as-is, not affecting any existing Image workflow—the Raw Image data can be extracted when needed, or ignored otherwise. We detail our approach and show its effectiveness against competing strategies.
-
Raw Image reconstruction using a self contained srgb jpeg Image with only 64 kb overhead
Computer Vision and Pattern Recognition, 2016Co-Authors: Rang M. H. Nguyen, Michael S. BrownAbstract:Most camera Images are saved as 8-bit standard RGB (sRGB) compressed JPEGs. Even when JPEG compression is set to its highest quality, the encoded sRGB Image has been significantly processed in terms of color and tone manipulation. This makes sRGB-JPEG Images undesirable for many computer vision tasks that assume a direct relationship between pixel values and incoming light. For such applications, the Raw Image format is preferred, as Raw represents a minimally processed, sensor-specific RGB Image with higher dynamic range that is linear with respect to scene radiance. The dRawback with Raw Images, however, is that they require large amounts of storage and are not well-supported by many imaging applications. To address this issue, we present a method to encode the necessary metadata within an sRGB Image to reconstruct a high-quality Raw Image. Our approach requires no calibration of the camera and can reconstruct the original Raw to within 0:3% error with only a 64 KB overhead for the additional data. More importantly, our output is a fully selfcontained 100% complainant sRGB-JPEG file that can be used as-is, not affecting any existing Image workflow - the Raw Image can be extracted when needed, or ignored otherwise. We detail our approach and show its effectiveness against competing strategies.
-
CVPR - Raw Image Reconstruction Using a Self-Contained sRGB-JPEG Image with Only 64 KB Overhead
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016Co-Authors: Rang M. H. Nguyen, Michael S. BrownAbstract:Most camera Images are saved as 8-bit standard RGB (sRGB) compressed JPEGs. Even when JPEG compression is set to its highest quality, the encoded sRGB Image has been significantly processed in terms of color and tone manipulation. This makes sRGB-JPEG Images undesirable for many computer vision tasks that assume a direct relationship between pixel values and incoming light. For such applications, the Raw Image format is preferred, as Raw represents a minimally processed, sensor-specific RGB Image with higher dynamic range that is linear with respect to scene radiance. The dRawback with Raw Images, however, is that they require large amounts of storage and are not well-supported by many imaging applications. To address this issue, we present a method to encode the necessary metadata within an sRGB Image to reconstruct a high-quality Raw Image. Our approach requires no calibration of the camera and can reconstruct the original Raw to within 0:3% error with only a 64 KB overhead for the additional data. More importantly, our output is a fully selfcontained 100% complainant sRGB-JPEG file that can be used as-is, not affecting any existing Image workflow - the Raw Image can be extracted when needed, or ignored otherwise. We detail our approach and show its effectiveness against competing strategies.
Ludovic Macaire - One of the best experts on this subject based on the ideXlab platform.
-
Spatio-spectral binary patterns based on multispectral filter arrays for texture classification.
Journal of the Optical Society of America. A Optics image science and vision, 2018Co-Authors: Sofiane Mihoubi, Benjamin Mathon, Olivier Losson, Ludovic MacaireAbstract:To discriminate gray-level texture Images, spatial texture descriptors can be extracted using the local binary pattern (LBP) operator. This operator has been extended to color Images at the expense of increased memory and computation requirements. Some authors propose to compute texture descriptors directly from Raw Images provided through a Bayer color filter array, which both avoids the demosaicking step and reduces the descriptor size. Recently, multispectral snapshot cameras have emerged to sample more than three wavelength bands using a multispectral filter array. Such cameras provide a Raw Image in which a single spectral channel value is available at each pixel. In this paper we design a local binary pattern operator that jointly extracts the spatial and spectral texture information directly from a Raw Image. Extensive experiments on a large dataset show that the proposed descriptor has both reduced computation cost and high discriminative power with regard to classical LBP descriptors applied to demosaicked Images.
-
Illumination-robust multispectral demosaicing
2017Co-Authors: Sofiane Mihoubi, Benjamin Mathon, Jean-baptiste Thomas, Olivier Losson, Ludovic MacaireAbstract:Snapshot multispectral cameras that are equipped with filter arrays acquire a Raw Image that represents the radiance of a scene over the electromagnetic spectrum at video rate. These cameras require a demosaicing procedure to estimate a multispectral Image with full spatio-spectral definition. Such a procedure is based on spectral correlation properties that are sensitive to illumination. In this paper, we first highlight the influence of illumination on demosaicing performances. Then we propose camera-, illumination-, and Raw Image-based normalisations that make demosaicing robust to illumination. Experimental results on state-of-the-art demosaicing algorithms show that such normalisations improve the quality of multispectral Images estimated from Raw Images acquired under various illuminations.
-
IPTA - Illumination-robust multispectral demosaicing
2017 Seventh International Conference on Image Processing Theory Tools and Applications (IPTA), 2017Co-Authors: Sofiane Mihoubi, Benjamin Mathon, Jean-baptiste Thomas, Olivier Losson, Ludovic MacaireAbstract:Snapshot multispectral cameras that are equipped with filter arrays acquire a Raw Image that represents the radiance of a scene over the electromagnetic spectrum at video rate. These cameras require a demosaicing procedure to estimate a multispectral Image with full spatio-spectral definition. Such a procedure is based on spectral correlation properties that are sensitive to illumination. In this paper, we first highlight the influence of illumination on demosaicing performances. Then we propose camera-, illumination-, and Raw Image-based normalisations that make demosaicing robust to illumination. Experimental results on state-of-the-art demosaicing algorithms show that such normalisations improve the quality of multispectral Images estimated from Raw Images acquired under various illuminations.
-
Multispectral demosaicing using pseudo-panchromatic Image
IEEE Transactions on Computational Imaging, 2017Co-Authors: Sofiane Mihoubi, Benjamin Mathon, Olivier Losson, Ludovic MacaireAbstract:Single-sensor color cameras, which classically use a color filter array (CFA) to sample RGB channels, have recently been extended to the multispectral domain. To sample more than three wavelength bands, such systems use a multispectral filter array (MSFA) that provides a Raw Image in which a single channel value is available at each pixel. A demosaicing procedure is then needed to estimate a fully-defined multispectral Image. In this paper, we review multispectral demosaicing methods and propose a new one based on the pseudo-panchromatic Image (PPI). Pixel values in the PPI are computed as the average spectral values. Experimental results show that our method provides estimated Images of better quality than classical ones.
-
Multispectral Demosaicing using Intensity-based Spectral Correlation
2015Co-Authors: Sofiane Mihoubi, Benjamin Mathon, Olivier Losson, Ludovic MacaireAbstract:Single-sensor color cameras, which classically use a color filter array (CFA) to sample RGB channels, have recently been extended to the multispectral domain. To sample more than three wavelength bands, such systems use a multispectral filter array (MSFA) that provides a Raw Image in which a single channel level is available at each pixel. A demosaicing procedure is then needed to estimate a multispectral Image with full spectral resolution. In this paper, we propose a new demosaicing method that takes spectral and spatial correlations into account by estimating the level for each channel. Experimental results show that it provides estimated Images of better quality than classical methods.
Sofiane Mihoubi - One of the best experts on this subject based on the ideXlab platform.
-
Snapshot multispectral Image demosaicing and classification
2018Co-Authors: Sofiane MihoubiAbstract:Multispectral cameras sample the visible and/or the infrared spectrum according to specific spectral bands. Available technologies include snapshot multispectral cameras equipped with filter arrays that acquire Raw Images at video rate. Raw Images require a demosaicing procedure to estimate a multispectral Image with full spatio-spectral definition. In this manuscript we review multispectral demosaicing methods and propose a new one based on the pseudo-panchromatic Image estimated directly from the Raw Image. We highlight the influence of illumination on demosaicing performances, then we propose pre- and post-processing normalization steps that make demosaicing robust to acquisition properties. Experimental results show that our method provides estimated Images of better objective quality than classical ones and that normalization steps improve the quality of state-of-the art demosaicing methods on Images acquired under various illuminations. Multispectral Images can be used for texture classification. To perform texture analysis, local binary pattern operators extract texture descriptors from color texture Images. We extend these operators to multispectral texture Images at the expense of increased memory and computation requirements. We propose to compute texture descriptors directly from Raw Images, which both avoids the demosaicing step and reduces the descriptor size. For this purpose, we design a local binary pattern operator that jointly extracts the spatial and spectral texture information from a Raw Image. In order to assess classification on multispectral Images we have proposed the first significant multispectral database of close-range textures in the visible and near infrared spectral domains. Extensive experiments on this database show that the proposed descriptor has both reduced computational cost and high discriminating power with regard to classical local binary pattern descriptors applied to demosaiced Images.
-
Spatio-spectral binary patterns based on multispectral filter arrays for texture classification.
Journal of the Optical Society of America. A Optics image science and vision, 2018Co-Authors: Sofiane Mihoubi, Benjamin Mathon, Olivier Losson, Ludovic MacaireAbstract:To discriminate gray-level texture Images, spatial texture descriptors can be extracted using the local binary pattern (LBP) operator. This operator has been extended to color Images at the expense of increased memory and computation requirements. Some authors propose to compute texture descriptors directly from Raw Images provided through a Bayer color filter array, which both avoids the demosaicking step and reduces the descriptor size. Recently, multispectral snapshot cameras have emerged to sample more than three wavelength bands using a multispectral filter array. Such cameras provide a Raw Image in which a single spectral channel value is available at each pixel. In this paper we design a local binary pattern operator that jointly extracts the spatial and spectral texture information directly from a Raw Image. Extensive experiments on a large dataset show that the proposed descriptor has both reduced computation cost and high discriminative power with regard to classical LBP descriptors applied to demosaicked Images.
-
Illumination-robust multispectral demosaicing
2017Co-Authors: Sofiane Mihoubi, Benjamin Mathon, Jean-baptiste Thomas, Olivier Losson, Ludovic MacaireAbstract:Snapshot multispectral cameras that are equipped with filter arrays acquire a Raw Image that represents the radiance of a scene over the electromagnetic spectrum at video rate. These cameras require a demosaicing procedure to estimate a multispectral Image with full spatio-spectral definition. Such a procedure is based on spectral correlation properties that are sensitive to illumination. In this paper, we first highlight the influence of illumination on demosaicing performances. Then we propose camera-, illumination-, and Raw Image-based normalisations that make demosaicing robust to illumination. Experimental results on state-of-the-art demosaicing algorithms show that such normalisations improve the quality of multispectral Images estimated from Raw Images acquired under various illuminations.
-
IPTA - Illumination-robust multispectral demosaicing
2017 Seventh International Conference on Image Processing Theory Tools and Applications (IPTA), 2017Co-Authors: Sofiane Mihoubi, Benjamin Mathon, Jean-baptiste Thomas, Olivier Losson, Ludovic MacaireAbstract:Snapshot multispectral cameras that are equipped with filter arrays acquire a Raw Image that represents the radiance of a scene over the electromagnetic spectrum at video rate. These cameras require a demosaicing procedure to estimate a multispectral Image with full spatio-spectral definition. Such a procedure is based on spectral correlation properties that are sensitive to illumination. In this paper, we first highlight the influence of illumination on demosaicing performances. Then we propose camera-, illumination-, and Raw Image-based normalisations that make demosaicing robust to illumination. Experimental results on state-of-the-art demosaicing algorithms show that such normalisations improve the quality of multispectral Images estimated from Raw Images acquired under various illuminations.
-
Multispectral demosaicing using pseudo-panchromatic Image
IEEE Transactions on Computational Imaging, 2017Co-Authors: Sofiane Mihoubi, Benjamin Mathon, Olivier Losson, Ludovic MacaireAbstract:Single-sensor color cameras, which classically use a color filter array (CFA) to sample RGB channels, have recently been extended to the multispectral domain. To sample more than three wavelength bands, such systems use a multispectral filter array (MSFA) that provides a Raw Image in which a single channel value is available at each pixel. A demosaicing procedure is then needed to estimate a fully-defined multispectral Image. In this paper, we review multispectral demosaicing methods and propose a new one based on the pseudo-panchromatic Image (PPI). Pixel values in the PPI are computed as the average spectral values. Experimental results show that our method provides estimated Images of better quality than classical ones.
Toshiyuki Asakura - One of the best experts on this subject based on the ideXlab platform.
-
Robust scene recognition using a GA and real-world Raw-Image
Measurement, 2001Co-Authors: Mamoru Minami, Julien Agbanhan, Toshiyuki AsakuraAbstract:Abstract This paper presents a new concept of scene recognition by a genetic algorithm (GA), using the 2-D gray-scale Image of a working space, termed here as Raw-Image, and a model shaping the 2-D top-surface of a target object. In fact here, the problem of object recognition in the Raw-Image is changed into an optimization problem of a model-based evaluation function. We make use in this research of a GA, as a search and optimization method. This GA employs a model-based fitness function as its objective function to perform the search of a target in the Raw-Image. In this research, three object models, namely a frame model, a surface model, and a surface-strips model are investigated in order to determine which one is the best for scene recognition in a noisy environment. Also, in order to appraise the recognition performance of each model, a comparative study is performed by analyzing the answers to the following criteria questions: sensitivity, reliability, and speed. The effectiveness of the method has been verified through experiments using real-world Raw-Images, and the method has shown its robustness of object recognition with the surface-strips model, in spite of the noises in the scene.
-
GA-model based robust scene recognition for indoor mobile robots traveling operations using Raw-Image
2000 26th Annual Conference of the IEEE Industrial Electronics Society. IECON 2000. 2000 IEEE International Conference on Industrial Electronics Contr, 1Co-Authors: J. Agbanhan, Mamoru Minami, H. Suzuki, Toshiyuki AsakuraAbstract:Recognition of a working environment is critical for an autonomous vehicle such as a mobile robot to confirm its possible intelligence. Therefore it is necessary to equip a recognition system with a sensor, which can get environmental information. As an effective sensor, a CCD camera is generally thought to be useful for all kinds of mobile robots. However, it is thought to be hard to use the CCD camera for visual feedback, which requires acquisition of the information in real-time. This research presents a corridor recognition method using unprocessed gray-scale Images, termed here the Raw-Images, and a genetic algorithm (GA), without any Image information conversion, so as to perform the recognition process in real-time. The robustness of the method against noises in the environment, and the effectiveness of the method for real-time recognition have been verified using real corridor Images.
