Font Size: a A A

Research On Technology Of Iris Recognition System

Posted on:2007-07-14Degree:MasterType:Thesis
Country:ChinaCandidate:Z LiuFull Text:PDF
GTID:2178360212971584Subject:Computer Science and Technology
Abstract/Summary:PDF Full Text Request
Biometrics of human being play an important role in our life and iris has become one of the most momentous features in people identification. The emphases and difficulty in iris recognition are also pointed. In this paper, iris recognition technology is studied profoundly from three thesis including iris image preprocessing, image features extraction and encoding, pattern matching and classifier designing. These will be discussed as follows:An Edge Detection Threshold Analysis Method (EDTAM) based on statistical principle is given to distill the external boundary pixels of iris; minimum ercheng is used to get the center and radius of the iris.Conventional iris feature extracting and encoding methods are discussed and analyzed in detail. Two improved algorithms based on Zero Spectral Moment Filters (ZSMF) and 1D Features extracting are given.Method of pattern matching and classifier designing are studied and a new classifier is given. That is Spectral Information Divergence and Spectral Angle Mapper(SIDASAM) classifier.At the final of the paper, the implement of algorithms mentioned above is described in which data come from CASIA iris image database. The result is also given. It is shown from theory and practical test that the improved algorithms given in this paper are better than traditional iris recognition methods. At the same time, the methods can avoid the effect of illumination, translation, rotation, scale variant, and have better stability and robustness.
Keywords/Search Tags:Biometric, Iris Recognition, Pattern Recognition, Iris Location, Feature Extraction, Pattern Matching, Classifier
PDF Full Text Request
Related items