Automatic Segmentation of Overlapped Images

Chromosomes are essential genomic information carriers. The identification of chromosome abnormalities is an essential part of diagnosis and treatment of genetic disorders such as chromosomal syndromes and many types of cancer. There are different types of chromosome aberration like mapping of the common duplications, deletions, and translocations. One of the most considerations in the field of chromosome analysis is the segmentation. Currently available cytogenetic imaging software is designed to classify only normal chromosomes [9]. The automation of chromosome analysis is involving segmentation of chromosomes and classification into 24 groups [8]. The segmentation and overlap of chromosomes are a major step toward the realization of homolog classification. Resolving chromosome overlaps is an unsolved problem in automated chromosome analysis and the analysis is complicated by the occurrence of clusters of overlapped chromosomes. Current systems for automatic chromosome classification are mostly interactive and require human intervention for correct separation between touching and overlapping chromosomes, and so are unable to segregate overlapping chromosomes. In this paper, propose an automatic procedure to obtain the separated chromosomes. The overlapped chromosomes are segmented by found the interesting (concave and convex) points with the help of chain code algorithm and the interesting points [1] are located on contour of the image and then the curvature function is found to find out concave points and the possible separation lines are plotted by using all concave points and finally construct hypotheses for possible separation lines between concave points. The segmentation is carried out by means of a curvature function scheme, which proved to be