Method for identity recognition through extracting iris texture characteristic

Abstract

The invention discloses a method for carrying out identification by extracting the textural property of iris. The method of the invention comprises the steps that two-dimension wavelet packet decomposition is carried out to an iris image after normalization treatment; quantization coding is carried out to subgraph coefficients, meanwhile, the airspace and frequency domain information of texture is extracted, and finally, Manhattan Distance is used as a classifier to obtain the result of identification. By adopting the iris recognition algorithm provided by the invention, higher rate of accuracy of identification and better noise-resistant performance can be obtained, furthermore, running speed is faster, thus meeting the requirement of real-time performance of a system.

Description

【Technical field】 [0001] The invention relates to a method for identity recognition by extracting iris texture features, in particular to a method for how to use two-dimensional wavelet packets to extract iris texture features for identity recognition. 【Background technique】 [0002] With the development of information technology and the wide application of electronic business, information security has gradually become an important and urgent problem that people are facing. Therefore, biometric identification technology, which can be used for identity authentication and information security protection, has been paid more and more attention by people. The so-called biometric identification technology refers to the close combination of computer and high-tech means such as optics, acoustics, biosensors and biostatistics, and uses the inherent physiological and behavioral characteristics of the human body to identify personal identities. The iris feature recognition technology ...

AI Technical Summary

Problems solved by technology

Although the second algorithm overcomes the limitations of the previous system caused by drift, rotation and scaling, it is also insensitive to brightness changes and noise, and does not require very high quality of captured images.

However, because the algorithm only uses part of the iris texture feature information, it does not obtain a high correct recognition rate.

The third algorithm uses a different texture analysis strategy to extract texture features, and obtains a faster running speed, but it describes the iris texture relatively rough, and the correct recognition rate is not as high as the first algorithm.

Images