A new approach for image segmentation with MATLAB

Image segmentation is the first step in many computer vision methods and serves to simplify the problem by grouping the pixels in the image in logical ways. Here we develop a new approach to deal with the problem of image segmentation in the framework of MATLAB programming environment which integrates thresholding, edge extraction and color information and shows good results when applied to some sample images. Further, we describe the merits and demerits of the proposed algorithm. In fact we can use this segmentation technique as an improvement over the in-built MATLAB ´edge detection´ function.