A Research Of Human Kayotype Analysis System

Chromosome Karyotyping, the classical method in the technology of chromosome genetic analysis, is one of the important means in genetic research and supplementary clinical diagnosis. And it is the key index to analyze chromosome translocation or deficiency, and diagnosis of a variety of genetic diseases. With the development of pattern recognition, and image processing methods begin widely used in medicine; automatic chromosome analysis become possible. This paper mainly researches on numerical analysis and processing method of biologically medical image on the background of image processing and pattern recognition of human Chromosome images. Some important technologies and core algorithms used in the system are discussed in detail, including the algorithms of image pre-processing, feature measurement, selection and classification. The main results and achievements are show as follows:1. This paper puts forward a kind of method suitable for human Chromosome images segmentation including some procedures such as gradient binary, area-filling utilizing brim characteristics, etc. Additionally, discussion and trial have been touched on Medial axis extraction of Human Chromosome images. The experiment results show that image pre-processing procedure of this system proposed in this article can effectively extract Chromosome outline and medial-axis-line, which has formed a good foundation for extracting Chromosome characteristics.2. This paper relates the method of extracting length, centromeric index and density profile from human Chromosome images. At first, the feature of displaying border is standardized by means of interpolation so that their dimensions are united, and evenly distributed along medial-axis line unity so as to strength the comparability of the feature of displaying border. Furthermore, the methods of debarment and PCA were respectively used to reduce their dimensions.3.The system apply method of Knowledge-based imitation geometric Category, use Chromosome length and Centromere index as main parameters, divide all Chromosome Into seven group: A,B,C,D,E,F,G then match then to stander chromosome. At last, Operator can do Manual match if the system can't Classification Correctly.