Analysis of Abnormality in Endoscopic images using Combined HSI Color Space and Watershed Segmentation

Author

Dhandra, B.V. ; Hegadi, Ravindra ; Hangarge, Mallikarjun ; Malemath, V.S.

Author_Institution

PG Dept. of Studies & Res. in Comput. Sci., Gulbarga Univ.

Volume

4

fYear

2006

fDate

2006

Firstpage

695

Lastpage

698

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

Keywords

endoscopes; feature extraction; filtering theory; image colour analysis; image reconstruction; image segmentation; inverse problems; mathematical morphology; medical image processing; transforms; HSI color space; average filter; endoscopic color images; endoscopic image abnormality analysis; grayscale image; image smoothing; inverse transform; morphological reconstruction; morphological watershed segmentation; pixel extraction; Computer aided diagnosis; Computer science; Gray-scale; Image analysis; Image color analysis; Image edge detection; Image segmentation; Pixel; Surface morphology; Surface topography;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2006. ICPR 2006. 18th International Conference on

Conference_Location

Hong Kong

ISSN

1051-4651

Print_ISBN

0-7695-2521-0

Type

conf

DOI

10.1109/ICPR.2006.268

Filename

1699936