A Image Thresholding Method Based on Binary Coded Ant Colony Algorithm

Image segmentation is the most significant step in image analysis and is a long-term difficult problem, which hasn't been fully solved. Many segmentation methods have been brought forward to deal with image segmentation, among these methods thresholding is the simple and important method in image segmentation. In practical work, 2-dimension (2D) entropy method is often used. It segments images by using the gray value of the pixel and the local average gray value of it, and thus provides better results than that of one-dimension entropy. However, for more accurate thresholding, much more time has to pay. Thus, this paper employs a novel approach to 2D threshold selection based on binary coded ant colony optimization algorithm. The proposed approach has been implemented and tested on several real images. Experiments results indicate that proposed method performs well which is a good method to help select optimum 2D thresholds.