A new evaluation measure for color image segmentation based on genetic programming approach

One of the greatest challenges while working on image segmentation algorithms is a comprehensive measure to evaluate their accuracy. Although there are some measures for doing this task, but they can consider only one aspect of segmentation in evaluation process. The performance of evaluation measures can be improved using a combination of single measures. However, combination of single measures does not always lead to an appropriate criterion. Besides its effectiveness, the efficiency of the new measure should be considered. In this paper, a new and combined evaluation measure based on genetic programming (GP) has been sought. Because of the nature of evolutionary approaches, the proposed approach allows nonlinear and linear combinations of other single evaluation measures and can search within many and different combinations of basic operators to find a good enough one. We have also proposed a new fitness function to make GP enable to search within search space effectively and efficiently. To test the method, Berkeley and Weizmann datasets besides several different experiments have been used. Experimental results demonstrate that the GP based approach is suitable for effective combination of single evaluation measures.