Classification of Abnormal Endoscopic Images using Morphological Watershed Segmentation

Segmentation by morphological watershed of images embodied many approaches such as detection of discontinuities, thresholding and region processing. In this paper the morphological watershed segmentation approach is implemented for the segmentation and analysis of possible presence of abnormality in endoscopic images. Here the gray scale imag e corresponding to the input color image is smoothed and bright spots are eliminated. 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. The presence of number of regions more than the threshold value in the output image will indicate the presence of abnormality in the image.

[1]  Luc Vincent,et al.  Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Shankar M. Krishnan,et al.  Intestinal abnormality detection from endoscopic images , 1998, Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol.20 Biomedical Engineering Towards the Year 2000 and Beyond (Cat. No.98CH36286).

[3]  V Pietropaolo,et al.  [Electronic video-endoscopy]. , 1987, Annali italiani di chirurgia.

[4]  P. S. Hiremath,et al.  Abnormality Detection in Endoscopic Images Using Color Segmentation and Curvature Computation , 2004, ICONIP.

[5]  Serge Beucher,et al.  Use of watersheds in contour detection , 1979 .

[6]  Luc Vincent,et al.  Morphological grayscale reconstruction in image analysis: applications and efficient algorithms , 1993, IEEE Trans. Image Process..