A genetic algorithm approach to color image enhancement

Abstract Image enhancement techniques are used to improve image quality or extract the fine details in the degraded images. Most existing color image enhancement techniques usually have three weaknesses: (1) color image enhancement applied in the RGB (red, green, blue) color space is inappropriate for the human visual system; (2) the uniform distribution constraint employed is not suitable for human visual perception; (3) they are not robust, i.e., one technique is usually suitable for one type of degradations only. In this study, a genetic algorithm (GA) approach to color image enhancement is proposed, in which color image enhancement is formulated as an optimization problem. In the proposed approach, a set of generalized transforms for color image enhancement is formed by linearly weighted combining four types of nonlinear transforms. The fitness (objective) function for GAs is formed by four performance measures, namely, the AC power measure, the compactness measure, the Brenner’s measure, and the information–noise change measure. Then GAs are used to determine the “optimal” set of generalized transforms with the largest fitness function value. Based on the experimental results obtained in this study, the enhanced color images by the proposed approach are better than that by any of the three existing approaches for comparison. This shows the feasibility of the proposed approach.

[1]  Jack Sklansky,et al.  A note on genetic algorithms for large-scale feature selection , 1989, Pattern Recognit. Lett..

[2]  K. Yamasaki,et al.  A dynamic routing control based on a genetic algorithm , 1993, IEEE International Conference on Neural Networks.

[3]  Michael D. Buchanan.  Effective Utilization Of Color In Multidimensional Data Presentations , 1979, Optics & Photonics.

[4]  Lawrence Davis,et al.  Genetic Algorithms and Simulated Annealing , 1987 .

[5]  David C. C. Wang,et al.  Digital image enhancement: A survey , 1983, Comput. Vis. Graph. Image Process..

[6]  Sankar K. Pal,et al.  Image enhancement incorporating fuzzy fitness function in genetic algorithms , 1993, [Proceedings 1993] Second IEEE International Conference on Fuzzy Systems.

[7]  Sankar K. Pal,et al.  Automatic selection of object enhancement operator with quantitative justification based on fuzzy set theoretic measures , 1990, Pattern Recognit. Lett..

[8]  Alexander Toet.  Multiscale color image enhancement , 1992, Pattern Recognit. Lett..

[9]  Jack D. Tubbs,et al.  A note on parametric image enhancement , 1987, Pattern Recognit..

[10]  I. M. Bockstein.  Color equalization method and its application to color image processing , 1986 .

[11]  Heinz Mühlenbein,et al.  Parallel Genetic Algorithms, Population Genetics, and Combinatorial Optimization , 1989, Parallelism, Learning, Evolution.

[12]  Frederick E. Petry,et al.  Scene recognition using genetic algorithms with semantic nets , 1990, Pattern Recognit. Lett..

[13]  O. Faugeras.  Digital color image processing within the framework of a human visual model , 1979 .

[14]  Gilbert Syswerda,et al.  Uniform Crossover in Genetic Algorithms , 1989, ICGA.

[15]  Robin N. Strickland,et al.  Digital Color Image Enhancement Based On The Saturation Component , 1987 .

[16]  L. Zadeh.  Calculus of fuzzy restrictions , 1996 .

[17]  R. Hummel.  Histogram modification techniques , 1975 .

[18]  Panos Trahanias,et al.  Color image enhancement through 3-D histogram equalization , 1992, Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol. III. Conference C: Image, Speech and Signal Analysis,.

[19]  John O. Limb,et al.  Distortion Criteria of the Human Viewer , 1979, IEEE Transactions on Systems, Man, and Cybernetics.