Automatic Determination of The G-band Chromosomes Number based on Geometric Features

Abstract

One of the source used to diagnose the genetic disorders and abnormalities is the light microscopic images of the chromosomes. The first step to check for the abnormalities is to count the chromosome. Many researches have been done on chromosome counting from the images, but the results still need an improvement on complicated case, the cluster of mixing patterns of chromosomes including touching, overlapping, and other patterns. The main objective of this research is to focus and increase the performance of chromosome number determination especially the cluster with the complicated pattern of chromosome. The paper presents a new technique, to determine the number of complicated chromosome image (DNCC) using geometric features including endpoints, and intersection points of the skeletonized chromosome image after pre-processing. The results yield 100% for the clusters with single chromosome, 100% for the clusters with overlapping of two chromosomes, and 79.12% for the cluster of complicated patterns of chromosomes.