A robust dynamic niching genetic clustering approach for image segmentation
Dongxia Chang, Yao Zhao, Yanhui Xiao · 2011
In this paper, a novel genetic clustering algorithm based on dynamic niching (DNGA) for image segmentation is proposed. It is an effective and robust approach to image segmentation on the basis of a total similarity function relating to the approximate density shape estimation. In the new algorithm, a dynamic identification of the niches is performed at each generation to automatically evolve the proper number of clusters and appropriate cluster centers of the data set. Moreover, a local search method is embeded in the evolutionary process which makes the dynamic niching method insensitive to the radius of the niche. Compared to existing methods, DNGA algorithm does not need to pre-specify the number of segmentation. Several images are used to demonstrate its superiority. The experimental results show that DNGA algorithm has high performance, effectiveness and flexibility.