1Department of Computer Applications, Velammal College of Management and Computer Studies, Ambattur Redhills Road, Chennai, Tamilnadu, India.
2RMD Engineering College, Kavarapettai, Chennai, Tamilnadu, India.
In the field of Biomedicine, because of cells complex nature, it still remains a challenging task to segment cells from its background and count them automatically. In this paper we show a new technique of image segmentation that uses an extended h-maxima transformation to find the possible cell locations and seeded watershed algorithm for cell segmentation. The over segmentation problem of watershed algorithm is reduced by morphological erosion which enables accurate result in low contrast images. The number of cells in the image was also found along with the average cell size. Applying this method to a difficult data set 96% of the cells in the image were identified.
Stem cell detection, counting, image enhancement and segmentation
