Application of Watershed Algorithms to Mammogram Image Analysis

Abstract

The objective of this article is to present a novel segmentation method giving realistic results on application of recursive watershed algorithm on mammogram images. We apply here a simple watershed transform which gives a clear segmentation of mammogram image for identification of any abnormal growth of tissues / tumors/cysts in the breast. We describe here the technique of repetitive watersheds and its results. Also we discuss about the marker and its application to avoid over segmentation.

Additional information

Notes on contributors

H S Sheshadri

H S Sheshadri received BE degree in Electronics and Communication Engineering from University of Mysore during 1979 and ME (Applied Electronics) under Bharatiar university during 1989. Currently he is pursuing PhD degree from Anna University, and working as a research scholar at the department of EEE, PSG College of Technology, Coimbatore under QIP. His area of research is on Biomedical image analysis. He is a life member of ISTE and an active member of IETE, Mysore Subcenter. He is a faculty at the department of E&C engineering, PES college of Engineering, Mandya and having 24 years of teaching experience.

A Kandaswamy

A Kandaswamy received BE (Honors) in Electrical Engineering in the year 1969 and MSc (Engg) in applied electronics in the year 1973 both from Madras University. Obtained Doctorate degree from Bharatiar University during 1995. He has served the department of EEE of PSG college of Technology at various capacities and was the Head of the Department of ECE for several years. He is now professor (Emeritus) at the department of ECE, PSG College of Technology. His area of interest is on Bomedical instrumentation, Biomedical Imaging, Biomedical Expert systems and Education technology. He is an active member of various societies like IEEE, BMSI, IE (India) etc. He is a technical reviewer of various National and International journals.