Iris Image Recognition Technology

Biometrics is a new subject which used the physiology and modality characteristics as the medium to identify people uniquely. Iris has the characteristic such as stabilization, individual differentia, non-invasion, which provides the iris identification with excelsior accuracy. It is being attended more and more by academia and has a potential and wider foreground.In this paper, the development of biometric recognition and some kinds of representative biometric recognition techniques are introduced. Then the development and meaning of iris recognition technique and the structure of iris recognition system are discussed in detail. The algorithm of iris recognition has also been researched deeply and of the processes including pre-processing, location, normalization, feature extraction, and pattern match are also have been carried out. Noise detecting and location have been focused on researching since they are the key steps of them.In the iris localization respect, we use Point Hough Transform (PHT) to localize the iris inner boundary and the outer boundary is localized through the Integral-differential method. When localizing outer boundary, as it can be easily disturbed by the noise from eyelids, we separate the eyelids before localizing the outer iris boundary. By using this method we have raised the accuracy of the iris localization.As there are some uncertain and unstable factors of instability between the equipment and person, the captured iris image contains not only the iris information, but also the eyelids, eyelash, reflection and so on. The disturbed factors will influence iris localization and feature extraction and eventually lead to lower recognition rate. As the eyelids are approximate to line and iris texture is little, we fit it with straight line. A fast method of eyelids localization using line stimulant is brought forward in this paper and we have improved the method of double threshold to detecting the eyelashes.For the purpose of dispel the influence of the elastic deformation in iris texture, it needs to normalize iris pattern. This was achieved by implementing the method presented by Yunhong Wang, where unwrapped the annular iris counter-clockwise to a rectangular texture block with a fixed size. The normalization nor only reduces to a certain extent the distortion of the iris caused by pupil movement but also simplifies subsequent processing.In the respect of iris recognition and classification, features of the iris were encoded by convolving the normalized iris region with ID Log-Gabor filters and phase quantizing the output in order to produce a bit-wise biometric template and noise mask. The Hamming distance was chosen as a matching metric, which gave a measure of how many bits disagreed between two templates. The two templates were deemed to have been generated from the same iris if the Hamming distance produced was lower than a set Hamming distance. Extensive experimental result shows the system performed with perfect recognition .Therefore, iris recognition is shown to be a reliable and accurate biometric technology.At last the result and conclusions of the paper are pointed out. At the same time, some expectations to future research are predicted.