Abstract: Color constancy refers to the ability of the human visual system to stabilize
the color appearance of surfaces under an illuminant change. In this work we studied how the interrelations among nine colors are perceived under illuminant changes, particularly whether they remain stable across 10 different conditions (5 illuminants and 2 backgrounds). To do so we have used a paradigm that measures several colors under an immersive state of adaptation. From our measures we defined a perceptual structure descriptor that is up to 87% stable over all conditions, suggesting that color category features could be used to predict color constancy. This is in agreement with previous results on the stability of border categories [1,2] and with computational color constancy
algorithms [3] for estimating the scene illuminant.

Abstract: The characterization of trichromatic cameras is usually done in terms of a device-independent color space, such as the CIE 1931 XYZ space. This is indeed convenient since it allows the testing of results against colorimetric measures. We have characterized our camera to represent human cone activation by mapping the camera sensor's (RGB) responses to human (LMS) through a polynomial transformation, which can be “customized” according to the types of scenes we want to represent. Here we present a method to test the accuracy of the camera measures and a study on how the choice of training reflectances for the polynomial may alter the results.

Abstract: The dichromatic reflection model (DRM) predicts that color distributions form a parallelogram in color space, whose shape is defined by the body reflectance and the illuminant color. In this paper we resume the assumptions which led to the DRM and shortly recall two of its main applications domains: color image segmentation and photometric invariant feature computation. After having introduced the model we discuss several limitations of the theory, especially those which are raised once working on real-world uncalibrated images. In addition, we summerize recent extensions of the model which allow to handle more complicated light interactions. Finally, we suggest some future research directions which would further extend its applicability.

Abstract: Visual recognition is one of the main problems in computer vision that attempts to solve image understanding by deciding what objects are in images. This problem can be computationally solved by using relevant sets of visual features, such as edges, corners, color or more complex object parts. This thesis contributes to how color features have to be represented for recognition tasks.
Image features can be extracted following two different approaches. A first approach is defining handcrafted descriptors of images which is then followed by a learning scheme to classify the content (named flat schemes in Kruger et al. (2013). In this approach, perceptual considerations are habitually used to define efficient color features. Here we propose a new flat color descriptor based on the extension of color channels to boost the representation of spatio-chromatic contrast that surpasses state-of-the-art approaches. However, flat schemes present a lack of generality far away from the capabilities of biological systems. A second approach proposes evolving these flat schemes into a hierarchical process, like in the visual cortex. This includes an automatic process to learn optimal features. These deep schemes, and more specifically Convolutional Neural Networks (CNNs), have shown an impressive performance to solve various vision problems. However, there is a lack of understanding about the internal representation obtained, as a result of automatic learning. In this thesis we propose a new methodology to explore the internal representation of trained CNNs by defining the Neuron Feature as a visualization of the intrinsic features encoded in each individual neuron. Additionally, and inspired by physiological techniques, we propose to compute different neuron selectivity indexes (e.g., color, class, orientation or symmetry, amongst others) to label and classify the full CNN neuron population to understand learned representations.
Finally, using the proposed methodology, we show an in-depth study on how color is represented on a specific CNN, trained for object recognition, that competes with primate representational abilities (Cadieu et al (2014)). We found several parallelisms with biological visual systems: (a) a significant number of color selectivity neurons throughout all the layers; (b) an opponent and low frequency representation of color oriented edges and a higher sampling of frequency selectivity in brightness than in color in 1st layer like in V1; (c) a higher sampling of color hue in the second layer aligned to observed hue maps in V2; (d) a strong color and shape entanglement in all layers from basic features in shallower layers (V1 and V2) to object and background shapes in deeper layers (V4 and IT); and (e) a strong correlation between neuron color selectivities and color dataset bias.

Abstract: Nowadays, digital images are used in many areas in everyday life, but they tend to be big. This increases amount of information leads us to the problem of image data storage. For example, it is common to have a representation a color pixel as a 24-bit number, where the channels red, green, and blue employ 8 bits each. In consequence, this kind of color pixel can specify one of 224 ¼ 16:78 million colors. Therefore, an image at a resolution of 512 £ 512 that allocates 24 bits per pixel, occupies 786,432 bytes. That is why image compression is important. An important feature of image compression is that it can be lossy or lossless. A compressed image is acceptable provided these losses of image information are not perceived by the eye. It is possible to assume that a portion of this information is redundant. Lossless Image Compression is defined as to mathematically decode the same image which was encoded. In Lossy Image Compression needs to identify two features inside the image: the redundancy and the irrelevancy of information. Thus, lossy compression modifies the image data in such a way when they are encoded and decoded, the recovered image is similar enough to the original one. How similar is the recovered image in comparison to the original image is defined prior to the compression process, and it depends on the implementation to be performed. In lossy compression, current image compression schemes remove information considered irrelevant by using mathematical criteria. One of the problems of these schemes is that although the numerical quality of the compressed image is low, it shows a high visual image quality, e.g. it does not show a lot of visible artifacts. It is because these mathematical criteria, used to remove information, do not take into account if the viewed information is perceived by the Human Visual System. Therefore, the aim of an image compression scheme designed to obtain images that do not show artifacts although their numerical quality can be low, is to eliminate the information that is not visible by the Human Visual System. Hence, this Ph.D. thesis proposes to exploit the visual redundancy existing in an image by reducing those features that can be unperceivable for the Human Visual System. First, we define an image quality assessment, which is highly correlated with the psychophysical experiments performed by human observers. The proposed CwPSNR metrics weights the well-known PSNR by using a particular perceptual low level model of the Human Visual System, e.g. the Chromatic Induction Wavelet Model (CIWaM). Second, we propose an image compression algorithm (called Hi-SET), which exploits the high correlation and self-similarity of pixels in a given area or neighborhood by means of a fractal function. Hi-SET possesses the main features that modern image compressors have, that is, it is an embedded coder, which allows a progressive transmission. Third, we propose a perceptual quantizer (½SQ), which is a modification of the uniform scalar quantizer. The ½SQ is applied to a pixel set in a certain Wavelet sub-band, that is, a global quantization. Unlike this, the proposed modification allows to perform a local pixel-by-pixel forward and inverse quantization, introducing into this process a perceptual distortion which depends on the surround spatial information of the pixel. Combining ½SQ method with the Hi-SET image compressor, we define a perceptual image compressor, called ©SET. Finally, a coding method for Region of Interest areas is presented, ½GBbBShift, which perceptually weights pixels into these areas and maintains only the more important perceivable features in the rest of the image. Results presented in this report show that CwPSNR is the best-ranked image quality method when it is applied to the most common image compression distortions such as JPEG and JPEG2000. CwPSNR shows the best correlation with the judgement of human observers, which is based on the results of psychophysical experiments obtained for relevant image quality databases such as TID2008, LIVE, CSIQ and IVC. Furthermore, Hi-SET coder obtains better results both for compression ratios and perceptual image quality than the JPEG2000 coder and other coders that use a Hilbert Fractal for image compression. Hence, when the proposed perceptual quantization is introduced to Hi-SET coder, our compressor improves its numerical and perceptual e±ciency. When ½GBbBShift method applied to Hi-SET is compared against MaxShift method applied to the JPEG2000 standard and Hi-SET, the images coded by our ROI method get the best results when the overall image quality is estimated. Both the proposed perceptual quantization and the ½GBbBShift method are generalized algorithms that can be applied to other Wavelet based image compression algorithms such as JPEG2000, SPIHT or SPECK.

Abstract: In this thesis, we explore how to estimate the effects of the light interacting with the scene objects from a single image. To achieve this goal, we focus on recovering intrinsic components like reflectance, shading, or light properties such as color and position using deep architectures. The success of these approaches relies on training on large and diversified image datasets. Therefore, we present several contributions on this such as: (a) a data-augmentation technique; (b) a ground-truth for an existing multi-illuminant dataset; (c) a family of synthetic datasets, SID for Surreal Intrinsic Datasets, with diversified backgrounds and coherent light conditions; and (d) a practical pipeline to create hybrid ground-truths to overcome the complexity of acquiring realistic light conditions in a massive way. In parallel with the creation of datasets, we trained different flexible encoder-decoder deep architectures incorporating physical constraints from the image formation models.
In the last part of the thesis, we apply all the previous experience to two different problems. Firstly, we create a large hybrid Doc3DShade dataset with real shading and synthetic reflectance under complex illumination conditions, that is used to train a two-stage architecture that improves the character recognition task in complex lighting conditions of unwrapped documents. Secondly, we tackle the problem of single image scene relighting by extending both, the SID dataset to present stronger shading and shadows effects, and the deep architectures to use intrinsic components to estimate new relit images.

Abstract: In this article we provide an analysis of existing methods for the incorporation of color in bag-of-words based image representations. We propose a list of desired properties on which bases fusing methods can be compared. We discuss existing methods and indicate shortcomings of the two well-known fusing methods, namely early and late fusion. Several recent works have addressed these shortcomings by exploiting top-down information in the bag-of-words pipeline: color attention which is motivated from human vision, and Portmanteau vocabularies which are based on information theoretic compression of product vocabularies. We point out several remaining challenges in cue fusion and provide directions for future research.

Abstract: A significative percentage of the human population suffer from impairments in their capacity to distinguish or even see colours. For them, everyday tasks like navigating through a train or metro network map becomes demanding. We present a novel technique for extracting colour information from everyday natural stimuli and presenting it to visually impaired users as pleasant, non-invasive sound. This technique was implemented inside a Personal Digital Assistant (PDA) portable device. In this implementation, colour information is extracted from the input image and categorised according to how human observers segment the colour space. This information is subsequently converted into sound and sent to the user via speakers or headphones. In the original implementation, it is possible for the user to send its feedback to reconfigure the system, however several features such as these were not implemented because the current technology is limited.We are confident that the full implementation will be possible in the near future as PDA technology improves.

Abstract: Color and texture are visual cues of different nature, their integration in an useful visual descriptor is not an easy problem. One way to combine both features is to compute spatial texture descriptors independently on each color channel. Another way is to do the integration at the descriptor level. In this case the problem of normalizing both cues arises. In this paper we solve the latest problem by fusing color and texture through distances in texton spaces. Textons are the attributes of image blobs and they are responsible for texture discrimination as defined in Julesz’s Texton theory. We describe them in two low-dimensional and uniform spaces, namely, shape and color. The dissimilarity between color texture images is computed by combining the distances in these two spaces. Following this approach, we propose our TCD descriptor which outperforms current state of art methods in the two different approaches mentioned above, early combination with LBP and late combination with MPEG-7. This is done on an image retrieval experiment over a highly diverse texture dataset from Corel.