Evolving Color Constancy for an Artificial Retina

Objects retain their color in spite of changes in the wavelength and energy composition of the light they reflect. This phenomenon is called color constancy and plays an important role in computer vision research. We have used genetic programming to automatically search the space of programs to solve the problem of color constancy for an artificial retina. This retina consists of a two dimensional array of elements each capable of exchanging information with its adjacent neighbors. The task of the program is to compute the intensities of the light illuminating the scene. These intensities are then used to calculate the reflectances of the object. Randomly generated color Mondrians were used as fitness cases. The evolved program was tested on artificial Mondrians and natural images.

[1]  Brian V. Funt,et al.  Committee-Based Color Constancy , 1999, CIC.

[2]  David H. Foster,et al.  Space-average scene colour used to extract illuminant information , 1997 .

[3]  David A. Forsyth,et al.  A Novel Approach To Colour Constancy , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[4]  Mark S. Drew,et al.  Separating a Color Signal into Illumination and Surface Reflectance Components: Theory and Applications , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[6]  Brian V. Funt,et al.  Color Constancy for Scenes with Varying Illumination , 1997, Comput. Vis. Image Underst..

[7]  David A. Forsyth,et al.  A novel algorithm for color constancy , 1990, International Journal of Computer Vision.

[8]  D H Brainard,et al.  Analysis of the retinex theory of color vision. , 1986, Journal of the Optical Society of America. A, Optics and image science.

[9]  Bernt Schiele,et al.  Comprehensive Colour Image Normalization , 1998, ECCV.

[10]  Berthold K. P. Horn.  Robot vision , 1986, MIT electrical engineering and computer science series.

[11]  Steven A. Shafer,et al.  Supervised color constancy for machine vision , 1991, Electronic Imaging.

[12]  M D'Zmura,et al.  Mechanisms of color constancy. , 1986, Journal of the Optical Society of America. A, Optics and image science.

[13]  John K. Tsotsos,et al.  From [R, G, B] to Surface Reflectance: Computing Color Constant Descriptors in Images , 1987, IJCAI.

[14]  John R. Koza,et al.  Genetic programming 2 - automatic discovery of reusable programs , 1994, Complex Adaptive Systems.

[15]  Leif H. Finkel,et al.  A multistage neural network for color constancy and color induction , 1995, IEEE Trans. Neural Networks.

[16]  S. Zeki.  A vision of the brain , 1993 .

[17]  Mark S. Drew,et al.  Color constancy computation in near-Mondrian scenes using a finite dimensional linear model , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[18]  L. Maloney,et al.  Color constancy: a method for recovering surface spectral reflectance. , 1986, Journal of the Optical Society of America. A, Optics and image science.

[19]  Brian V. Funt,et al.  Learning Color Constancy , 1996, CIC.

[20]  Brian V. Funt,et al.  Is Machine Colour Constancy Good Enough? , 1998, ECCV.

[21]  Jeanny Hérault.  A model of colour processing in the retina of vertebrates: From photoreceptors to colour opposition and colour constancy phenomena , 1996, Neurocomputing.

[22]  Inman Harvey,et al.  Issues in evolutionary robotics , 1993 .

[23]  Mark S. Drew,et al.  Color constancy from mutual reflection , 1991, International Journal of Computer Vision.