Analysis of abnormality in endoscopie images using combined HSI color space and watershed segmentation

Abstract

In this paper, a method for detecting possible presence of abnormality in the endoscopic images is presented. The pre-processed endoscopic color images are segmented in the HSI color space. The pixels in the input color image corresponding to the segmented image are extracted for further processing. This image is smoothened using average filter and converted into grayscale image. Its inverse transform is obtained for further processing and extended minima is imposed on the processed image using morphological reconstruction. Then the morphological watershed segmentation is carried out on this image and the number of regions is counted and is compared with the threshold value. If the number of regions is more than the threshold value, then the output image is an indicative of possible presence of abnormality in the image. © 2006 IEEE.