Algorithms for Image Segmentation

In image analysis, segmentation is the partitioning of a digital image into multiple regions (sets of pixels), according to some homogeneity criterion. The problem of segmentation is a well-studied one in literature and there are a wide variety of approaches that are used. Different approaches are suited to different types of images and the quality of output of a particular algorithm is difficult to measure quantitatively due to the fact that there may be many “correct” segmentations for a single image. Here, a graphtheoretic framework is considered by modeling image segmentation as a graph partitioning and optimization problem using the normalized cut criterion. Comparisons with other criteria shows that the results for normalized cut are quite good although high computational complexity is a drawback.