Acquisition of color opponent representation by a three-layered neural network model

Abstract

This paper discusses color representation in the visual system by analysis of a three-layered neural network model. The model incorporates physiological knowledge of color representation at the sensor level (broad-band trichromatic representation by cones) and the higher level (narrow-band color representation by color-coded cells in V4). We trained the model to perform a mapping between these color representations by the back propagation algorithm and analyzed the acquired characteristics of the hidden units. It turned out that the hidden units learned characteristics similar to those of the color opponent cells found in the visual system. It was concluded that the R-G and Y-B color opponent representations reflect the efficiency of the color representation in the visual system from investigations on the efficiency of color representation in the hidden layer and on the capability of the color recognition task of the model.

Computer analysis of Van Gogh’s complementary colours

“…For instance, the red-green channel is very sensitive to complementarycolour pairs that include red and green. Experimental evidence suggests that the opponent channels arise naturally in artificial neural networks (Usui et al, 1994) or as the independent components of natural images (Lee et al, 2002;. Biological studies have revealed that individual neurons in the visual system respond to opponent-colours (De Valois and De Valois, 2000).…”

Opponent color processing based on neural models

“…Buchsbaum and Gottschalk [Buchsbaum 1983] have shown that efficient information transmission is achieved by opponent color coding. Usui et al [Usui 1991[Usui , 1994 trained neural network models by means of a backpropagation algorithm. The hidden units learned characteristics similar to those of opponent color cells known from neurobiology.…”