Homologue classification of human chromosome images using an iterative centromere segmentation algorithm

Segmentation of centromeres is a major step towards classification of homologous chromosomes, which in turn, is essential to advanced studies of cancer genetics. This paper describes an iterative fuzzy algorithm, which successfully segments the centromeres of human chromosome images. The algorithm is based on assigning a fuzzy membership value to each pixel and iteratively updating an error function, Chromosome 22 is then used to verify the centromere segmentation method.