| Biometric Recognition Technology develops very fast recently, which recognize people by means of some sole and stable features. The operation of this technology is convenient and rapid. Meanwhile, there doesn't exist problems such as cryptogram got out or card lost which is present in cryptogram identification and card identification respectively. So it is highly reliable and safe.During various external features of human body such as fingerprint, face, eye and iris, iris has very special structure which provides the iris identification with excelsior accuracy. Iris identification technology is regarded as one of the most promising biometric recognition technology.Others' algorithms of iris location are studied and the deficiencies in them are pointed. Two different approachs based on Mathematic Morphology and Hough Transform are advanced. While in the feature extraction, four ways are researched such as the means of encode of iris texture, the improved algorithm based on Daugman's, the approach of identification by means of the Fourier spectra of the transmission binary model of the human irises and the method of iris identification using wavelet transform. The advantages and disadvantages of these ways are compared. Improved algorithm based on wavelet transform is proposed and proves feasible.At last, the problems in iris recognition technology and the prospect of this technology are pointed.
|
PDF Full Text Request