Study On Algorithm Of Iris Feature Extraction And Recognition

Recently, biometric recognition technology develops very fast, which identify people by some sole and stable features. The operation of this technology is convenient and rapid. Meanwhile, It has not 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.Among various external features of human body such as fingerprint, face, eye and iris, iris has very special structures, which provides the iris identification with excelsior accuracy. Iris identification technology is regarded as one of the most promising biometric cognition technology.A personal identification system based on iris patterns is composed of iris image acquisition, image preprocessing, feature extraction and coding, matching and recognition.In image preprocessing of iris, two steps of coarse location and exact location is used to locate the center and radii of the inner and outer circle of iris, thus iris could be separated from the eye image. After finding parameter of coarse location, the inner and outer circle can be got based on the parameter because the circle of pupil and circle of iris nearly have the same center. In the step of exact location, the district method is adopted in view of the iris edge gradation jump characteristic to accurately to locate the iris the outside edge. The iris images separated become the unification the rectangular image through the normalization the iris image.The wavelet transformation is one kind of signal time-dimension (time-frequency) the analysis method; it has the multi-dimension resolution analysis the characteristic. The cross-zero detection of wavelet transform could detect the gradation image sudden change information, at the same time it could be express the characteristic information the original map (namely image function plants "jump point"). The technology of identification based on iris is researched in the article, the key point of the technology is the iris characteristic acquisition and recognition, therefore based on the iris image texture characteristic, using the wavelet transforms to get the characteristic of iris image, a new method named Zero-Crossing Detection and Secondary Circle Coding is used in the article. The experiment indicated that, it is very effective to use this way to get iris characteristic.