Automatic Multi-thresholds Selection for Image Segmentation based on Evolutionary Approach

Automatic thresholding has been widely used in machine vision for automatic image segmentation. Otsu's method selects an optimum threshold by maximizing the between-class variance in a grayscale image. However, the method becomes time-consuming when extended to multi-level threshold problems, because excessive iterations are required in order to compute the cumulative probability and the mean of class. In this paper, we focus on the issue of automatic selection. for multi-level thresholding, and we greatly improve the efficiency of Otsu's method for image segmentation based on evolutionary approaches. We have investigated and evaluated the performance of the Otsu and Valley-emphasis thresholding methods. Based on our evaluation results, we have developed many different algorithms for automatic threshold selection based on the evolutionary method using the Modified Adaptive Genetic Algorithm and the Hill Climbing Algorithm. The experimental results show that the evolutionary approach achieves a satisfactory segmentation effect and that the processing time can be greatly reduced when the number of thresholds increases.