Using eigencolor normalization for illumination-invariant color object recognition

Color constancy is of important for many computer vision applications, such as image classification, color object recognition, object tracking and so on. But unlike the human visual system, imaging device cannot be able to compute color constant descriptors which do not vary with the color of the illuminant, so solving color constancy problem is necessary. In the calculation of color constancy, illuminant estimation is the key. Because grey surfaces can perfectly reflect the color of the scene illumination, many methods have been proposed to identify grey surfaces to estimate the illuminant. But they either rely on the camera.s parameters, lacking universality, or work inaccurate in worse conditions. In order to solve these problems, in this paper, an iterative method is proposed. The quality of the proposed method is tested and compared to the previous color constancy methods on the Macbeth Chart and two data sets of synthetic and real images. Through MATLAB simulation, experimental pictures and quantitative data for performance evaluation were gotten. The simulated results show that the proposed algorithm is accurate and efficient in identification of the grey surfaces, even in worse condition. And it performs well in color constancy computation on both synthetic and real images.

Perception of colour depends on the spectral composition of light that reaches retina and depends as well on various mechanisms of visual system that processes information flow. The few important mechanisms can be distinguished in colour perception: colour adaptation, colour constancy and colour contrast. If the visual field has only one coloured object, then colour perception will be determined by spectral composition of the light and colour adaptation. Whereas mechanisms of colour constancy and colour contrast switches on when in the visual field there are at least two colour objects. Von Kries (1905) have attributed colour constancy phenomenon to theory of receptoral adaptation. But this is theory is applicable to local processes happening in relatively small size of visual field. Craven and Foster (1992) shows that receptor excitation ratios remains constant during change of illumination. But again remains unexplained colour change during adaptation. So, the hypothesis is raised that two processes attribute colour perception: local colour contrast calculation and global adaptation to the background. Therefore the experiments have been carried out to establish the colour contrast and background adaptation impact on colour perception.Four subjects with normal colour vision participated in the experiments. 40 Munsell samples (value 7 and chroma 4) illuminated with one reference illuminant (standard C) and 6 test illuminants (standard A, standard S, cardinal red, cardinal green, cardinal yellow and cardinal blue) were simulated on computer monitor. The dark-adapted subjects have been shown colour samples on neutral background illuminated with one of test illuminants. The task was to match the colour stimuli appearance under reference illuminant. The sequential asymmetric matching procedure was carried out. First subject adapts to neutral background under illuminan C then test stimulus and test background appears for limited time followed by readaptation to neutral background. Then subject is asked to adjust the colour mach under illuminant C. Two different experiment paradigms have been used. In the first one the stimulus had 2° on neutral background covering 20° of visual field. In the second paradigm the stimulus size was the same but the background was covering the all visual field. The adaptation and presentation timings were 1, 5, 30 or 60 seconds.Results under the first experiment paradigm show partial colour constancy for all subjects and for all test illuminants under various adaptation times. Despite quite a long adaptation time of 30 seconds subjects was unable to achieve full colour constancy. Colour constancy improves under second experiment paradigm. 60-second adaptation time is enough to achieve full colour constancy. The less adaptation time (1 or 30 second) gives partial colour constancy.The subject sees two colours (stimulus and background) during the experiment. The colour perception of stimulus and background changes during adaptation time. In the first 5 seconds of adaptation 40–60% of full adaptation level is reached (Fairchild and Reniff, 1995; Werner et al., 2000). Wesner and Shevell (1992, 1994) shown that signals from all visual field have influence on colour perception of object. The first part of our experiment shows that neutral background of 20° gives partial adaptation to background colour. Therefore, increase background illumination to full visual field gives full adaptation to background. So, subject perceives different coloured background under various illuminants as the same neutral (grey) background.We can state that two different systems have been distinguished in the process of colour perception. One system evaluates the colour difference between the stimulus and the background. Second system evaluates the colour of the background. Perceived colour difference during adaptation does not change much, but perceived colour of the background changes a lot and drifts towards neutral colour. The hypothesis of two level colour perception is supported by experimental data.

Ratios of excitations in each cone-photoreceptor class produced by light reflected from pairs of surfaces in a scene are almost invariant under natural illuminant changes. The stability of these spatially defined ratios may explain the remarkable ability of human observers to efficiently discriminate illuminant changes from changes in surface reflectances. Spatial cone-excitation ratios are not, however, exactly invariant. This study is concerned with observers' sensitivity to these invariance violations. Simulations of Mondrian paintings with either 49 or two natural surfaces under Planckian illuminants were presented as images on a computer-controlled display in a two-interval experimental design: in one interval, the surfaces underwent an illuminant change; in the other interval, the surfaces underwent the same change but the images were then corrected so that, for each cone class, ratios of excitations were preserved exactly. Although the intervals with corrected images corresponded individually to highly improbable natural events, observers systematically misidentified them as containing the illuminant changes, the probability of error increasing as the violation of invariance in the other interval increased. For the range of illuminants and surfaces tested, sensitivity to violations of invariance was found to depend on cone class: it was greatest for long-wavelength-sensitive cones and least for short-wavelength-sensitive cones. Spatial cone-excitation ratios, or some closely related quantities, seem to be the cues preferred by observers for making inferences about surface illuminant changes.

Computer based automatic medical image processing and quantification are becoming popular in digital pathology. However, preparation of histology slides can vary widely due to differences in staining equipment, procedures and reagents, which can reduce the accuracy of algorithms that analyze their color and texture information. To re- duce the unwanted color variations, various supervised and unsupervised color normalization methods have been proposed. Compared with supervised color normalization methods, unsupervised color normalization methods have advantages of time and cost efficient and universal applicability. Most of the unsupervised color normaliza- tion methods for histology are based on stain separation. Based on the fact that stain concentration cannot be negative and different parts of the tissue absorb different stains, nonnegative matrix factorization (NMF), and particular its sparse version (SNMF), are good candidates for stain separation. However, most of the existing unsupervised color normalization method like PCA, ICA, NMF and SNMF fail to consider important information about sparse manifolds that its pixels occupy, which could potentially result in loss of texture information during color normalization. Manifold learning methods like Graph Laplacian have proven to be very effective in interpreting high-dimensional data. In this paper, we propose a novel unsupervised stain separation method called graph regularized sparse nonnegative matrix factorization (GSNMF). By considering the sparse prior of stain concentration together with manifold information from high-dimensional image data, our method shows better performance in stain color deconvolution than existing unsupervised color deconvolution methods, especially in keeping connected texture information. To utilized the texture information, we construct a nearest neighbor graph between pixels within a spatial area of an image based on their distances using heat kernal in lαβ space. The representation of a pixel in the stain density space is constrained to follow the feature distance of the pixel to pixels in the neighborhood graph. Utilizing color matrix transfer method with the stain concentrations found using our GSNMF method, the color normalization performance was also better than existing methods.

Human has the visual system called "color constancy" that maintains the perceptive colors of same object across various light sources. The effective method of color constancy algorithm was proposed to use the human facial color in a digital color image, however, this method has wrong estimation results by the difference of individual facial colors. In this paper, we present the novel color constancy algorithm based on skin color analysis. The skin color analysis is the method to separate the skin color into the components of melanin, hemoglobin and shading. We use the stationary property of Japanese facial color, and this property is calculated from the components of melanin and hemoglobin. As a result, we achieve to propose the method to use subject's facial color in image and not depend on the individual difference among Japanese facial color.

Automatic detection metastasis in breast histopathological images based on ensemble learning and color adjustment

This paper proposes an approach to improve color images suffering from low dynamic range, by employing both histogram matching and histogram stretching techniques. Firstly, the color image is transformed from RGB into HSV color space, in which the color information is separated from intensity. Then, an appropriate reference image is selected by comparing component V of the enhancing image with component V of the data base images using a similarity measure. This selected image is used as the goal image in histogram matching algorithm in order to enhance image brightness (Automatic Histogram Matching). Secondly, components V and S are linearly stretched in order to recover the image color information. Finally, using the treated V and S components and untreated component of H, the enhanced image is obtained in RGB color space by inverse transform. The qualitative and quantitative results show that the contrast and color of resultant images are greatly improved using the proposed method, which outperforms the current state-of-the-art methods.

BackgroundThe advancements in unmanned aerial vehicle (UAV) technology have recently emerged as an effective, cost-efficient, and versatile solution for monitoring crop growth with high spatial and temporal precision. This monitoring is usually achieved through the computation of vegetation indices (VIs) from agricultural lands. The VIs are based on the incoming radiance to the camera, which is affected when there is a change in the scene illumination. Such a change will cause a change in the VIs and subsequent measures, e.g., the VI-based chlorophyll-content estimation. In an ideal situation, the results from VIs should be free from the impact of scene illumination and should reflect the true state of the crop’s condition. In this paper, we evaluate the performance of various VIs computed on images taken under sunny, overcast and partially cloudy days. To improve the invariance to the scene illumination, we furthermore evaluated the use of the empirical line method (ELM), which calibrates the drone images using reference panels, and the multi-scale Retinex algorithm, which performs an online calibration based on color constancy. For the assessment, we used the VIs to predict leaf chlorophyll content, which we then compared to field measurements.ResultsThe results show that the ELM worked well when the imaging conditions during the flight were stable but its performance degraded under variable illumination on a partially cloudy day. For leaf chlorophyll content estimation, The r^2 of the multivariant linear model built by VIs were 0.6 and 0.56 for sunny and overcast illumination conditions, respectively. The performance of the ELM-corrected model maintained stability and increased repeatability compared to non-corrected data. The Retinex algorithm effectively dealt with the variable illumination, outperforming the other methods in the estimation of chlorophyll content. The r^2 of the multivariable linear model based on illumination-corrected consistent VIs was 0.61 under the variable illumination condition.ConclusionsOur work indicated the significance of illumination correction in improving the performance of VIs and VI-based estimation of chlorophyll content, particularly in the presence of fluctuating illumination conditions.

Stereo retinex

Are there regions in a color space where color categories are invariant across illuminant changes? If so, what characteristics make them more stable than other regions? To address these questions, we asked observers to give a color name to 424 colored surfaces, presented one at a time, under various chromatic illuminants. Results showed a high degree of categorical color constancy, especially under illuminants that occur in the natural environment. It was also shown that surfaces selected as a focal color (the best example of a color category) are more resistant to illuminant change than nonfocal color samples. We additionally ran an asymmetric color matching experiment to quantify the shift of color appearance induced by illuminant changes using surfaces that were all named gray, thereby disentangling the appearance-based color constancy from the categorical color constancy (which are often confounded). Results suggested that the appearance of color samples largely shifted owing to illuminant changes, even though all samples were named gray; showing that the constancy of a color category is substantially more robust than the constancy of color appearance.

In this paper, we propose a novel model for the computational color constancy, inspired by the amazing ability of the human vision system (HVS) to perceive the color of objects largely constant as the light source color changes. The proposed model imitates the color processing mechanisms in the specific level of the retina, the first stage of the HVS, from the adaptation emerging in the layers of cone photoreceptors and horizontal cells (HCs) to the color-opponent mechanism and disinhibition effect of the non-classical receptive field in the layer of retinal ganglion cells (RGCs). In particular, HC modulation provides a global color correction with cone-specific lateral gain control, and the following RGCs refine the processing with iterative adaptation until all the three opponent channels reach their stable states (i.e., obtain stable outputs). Instead of explicitly estimating the scene illuminant(s), such as most existing algorithms, our model directly removes the effect of scene illuminant. Evaluations on four commonly used color constancy data sets show that the proposed model produces competitive results in comparison with the state-of-the-art methods for the scenes under either single or multiple illuminants. The results indicate that single opponency, especially the disinhibitory effect emerging in the receptive field's subunit-structured surround of RGCs, plays an important role in removing scene illuminant(s) by inherently distinguishing the spatial structures of surfaces from extensive illuminant(s).

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.

An unsupervised style normalization method for cytopathology images

Event Abstract Back to Event The effect of surface material on colour constancy in real world scenes Annette Werner1* and Lara Zebrowski1, 2 1 Tübingen University, Ophthalmology, Germany 2 Ophthalmology, Germany The visual appearance of real world objects depends on their reflectance properties, illumination and geometrical factors. We asked how human colour constancy performance deals with the depth-mesostructure of surfaces, which may provide additional cues or, alternatively, worsen colour constancy. In our experiments we presented samples (circular patches, 90 mm) of different materials (paper, fur, tile, cloth, leather), each mounted on a black sample holder (front 30 x 15 cm, 60 deg slope) and presented in the middle of a black viewing box (1.0 x 1.0 x 0.8 m). All samples appeared nearly achromatic under daylight. The samples and the box were illuminated by a computer controlled, calibrated LCD-projector (Panasonic PT AE 1000E) which was mounted above the observers' head. The observers (2 male, 2 female) viewed the samples frontally (viewing distance 90 cm). The chromaticity of the standard illuminant was D65, the equiluminant test-illuminants were chosen from one of the cardinal axes. After viewing the samples under the standard illuminant for 15 s, the respective test-illuminant was presented for 5 s. Colour constancy was quantified by a hue-cancellation method, whereby the observer adjusts the appearance of the sample so that it appears achromatic (“gray”) under the respective test illuminant. Colour constancy for the different materials was found not to differ significantly, but there was a trend for compensating illumination changes best for fur and worst for tile surfaces, across all illuminants and observers, with paper ranking in the middle. The possible role of depth-mesostructure as a cue for colour constancy is discussed. Acknowledgements Supported by BMBF grant FKZ 01GQ1002. Keywords: colour constancy, material &amp, surfaces, mesostructure, Perception Conference: Bernstein Conference 2012, Munich, Germany, 12 Sep - 14 Sep, 2012. Presentation Type: Poster Topic: Sensory processing and perception Citation: Werner A and Zebrowski L (2012). The effect of surface material on colour constancy in real world scenes. Front. Comput. Neurosci. Conference Abstract: Bernstein Conference 2012. doi: 10.3389/conf.fncom.2012.55.00051 Copyright: The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers. They are made available through the Frontiers publishing platform as a service to conference organizers and presenters. The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated. Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed. For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions. Received: 25 May 2012; Published Online: 12 Sep 2012. * Correspondence: Dr. Annette Werner, Tübingen University, Ophthalmology, Tübingen, 72070, Germany, annette.werner@uni-tuebingen.de Login Required This action requires you to be registered with Frontiers and logged in. To register or login click here. Abstract Info Abstract The Authors in Frontiers Annette Werner Lara Zebrowski Google Annette Werner Lara Zebrowski Google Scholar Annette Werner Lara Zebrowski PubMed Annette Werner Lara Zebrowski Related Article in Frontiers Google Scholar PubMed Abstract Close Back to top Javascript is disabled. Please enable Javascript in your browser settings in order to see all the content on this page.

In order to achieve a compact robot vision system that can perform object identification in real environments exposed to large changes in illumination, it is essential to consider both the algorithm and the hardware architecture. In this study, we have developed a compact and low-power image recognition system that is robust to illumination changes, consisting of a CMOS image sensor, field-programmable gate array (FPGA), and graphics processing unit (GPU) for embedded devices. To minimize the effects of changes in the illumination, our system uses the center/surround (C/S) retinex model, which is a color constancy model of the visual nervous system. Since the C/S retinex model involves large-scale spatial filtering with high computational costs, we compared the processing speeds of different hardware implementations of this model. This comparison showed that the FPGA implementation of the C/S retinex model used in this study is more than 10 times faster than the GPU implementation. Using the output of this efficiently processed C/S retinex model, a relatively small convolutional neural network (CNN), which runs on a GPU for embedded devices, performs object classification. We also investigated the impact of the spatial parameters of the C/S retinex model on the classification accuracy of CNNs using a dataset of images acquired under various lighting conditions. This investigation revealed parameters that provide better classification accuracy, and these parameters were largely independent of the CNN architecture used. This system performed object classification under various illumination colors at 52.1 frames per second with a power consumption of approximately 10.9 W.