Differential evolution embedded Otsu's method for optimized image thresholding

Image segmentation is a challenging task in digital image processing. Thresholding, an important technique for image segmentation, has gained considerable attention from the researchers for selecting reasonable thresholds. Since gray levels characterize the objects in a gray image, many thresholding methods extract objects from their background based on the statistics of one-dimensional (1D) histogram of gray levels and two-dimensional (2D) histogram of gray levels. A frequently used method is Otsu's method, which selects the global optimal threshold by maximizing the between-class variance. In this paper Differential Evolution (DE) has been embedded in Otsu's method for selecting an optimized threshold value. The proposed method is tested on a set of four images and the results validate the effectiveness of the proposed technique.