A Retinal Mechanism Inspired Color Constancy Model

Abstract

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).

Colour Constancy for Image of Non-Uniformly Lit Scenes

“…A biologically inspired model for colour constancy was reported by Gao et al [39] that exploits the response of the Double Opponent cells in different channels and estimates the colour of the illuminant by max or sum pooling mechanism in long, medium and short wavelength colour space. An improved retinal-mechanism-based model was proposed by Zhang et al [40]. The authors imitated the function of Horizontal Cell (HC) modulation that provides global colour correction with cone-specific lateral gain control.…”

Color Constancy by Reweighting Image Feature Maps

“…High priority -It is generally suggested that the ganglion cells within the retina are the basis of color processing mechanisms of human color constancy, which respond to the activations of cone photoreceptors at the very first stage of the human visual system [3,17]. Therefore, it makes more sense to perform the computational color constancy before the explorations of further semantic information.…”

“…Unfortunately, the photosensors in modern digital cameras do not possess the ability of automatically compensating for the illuminant colors. To address this issue, a variety of computational color constancy algorithms have been proposed to mimic the dynamical adjustments of the cones in the human visual system [1,2,3].Computational color constancy generally works by first estimating the illuminant color, and then compensating it by multiplying the reciprocal of the illuminant color to the color-biased image. Existing computational color constancy algorithms can be classified into a priori assumption-based ones and learning-based ones, according to whether a training process is needed.…”

“…In recent years, following the massive success of deep learning in computer vision community, high-level color constancy algorithms based on the convolutional neural network (CNN) have achieved state-of-the-art performances on the benchmark datasets [11,12,13]. However, we notice that many existing CNN-based models adopt the architectures from image classification domain, e.g., AlexNet [14] in [15], SqueezeNet [16] in [13], which are overcomplicated and inefficient when dealing with color-relevant applications.A PREPRINT -DECEMBER 24, 2018 Compared to visual recognition or understanding tasks, color constancy has its own unique properties:High priority -It is generally suggested that the ganglion cells within the retina are the basis of color processing mechanisms of human color constancy, which respond to the activations of cone photoreceptors at the very first stage of the human visual system [3,17]. Therefore, it makes more sense to perform the computational color constancy before the explorations of further semantic information.Condensation and superficiality -The useful cues for color constancy are highly condensed: if there exists neutral or specular regions in the image, computational color constancy can be done by pooling these regions in the spatial domain [18,19,20]; if there exists shading regions, it can be done by extracting these regions in the gradient domain [21].…”

Deep Learning-Based Computational Color Constancy With Convoluted Mixture of Deep Experts (CMoDE) Fusion Technique

“…The biological color constancy method is intended to mimic and apply the functional characteristics of the human visual system (HVS) to perform the learning-based illuminant estimation, and several models have been presented [32][33][34]. Gao et al [32] propose an HVS-based color rendering approach by taking after the interaction between the single-opponent (SO) cells in the retina, the double-opponent (DO) cells and any possible neurons in the human visual cortexes.…”