Chapter 7. Image Segmentation

Summary

Image segmentation is one of the most important steps in image processing. In this chapter various strategies of image segmentation have been presented. Various edge detection operators based on single derivatives, like Sobel, Robert, Prewit, Kirsch, and Canny edge operators have been discussed with sufficient detail. Isotropic edge operators like Laplacian operator have also been discussed. Thresholding forms an important strategy for image segmentation. Various thresholding techniques like entropy based thresholding have been discussed here. Other segmentation techniques like region growing, clustering based segmentation, waterfall algorithm for segmentation, and match based segmentation have been presented with adequate detail. Some important applications like document image segmentation have been briefly introduced.