Iris identification method based on multidirectional Gabor and Adaboost

Abstract

The invention relates to an iris identification method based on multidirectional Gabor and Adaboost. The method comprises the following steps that: (1), block division is carried out on a normalized iris image and two-dimensional Gabor characteristics are extract to carry out coding; and a Hanmming distance between corresponding blocks is calculated; and (2), an Adaboost algorithm is used to carry out classification and identification on the block Hanmming distance obtained in the step (1). More particularly, in the characteristic extraction process, Gabor wavelets of eight directions under a same scale are employed; and block division is carried out on the expanded iris image; Gabor characteristics of the whole iris image and submodules of the iris image are simultaneously extracted by combining integral and local information of the iris and then coding is carried out; the whole and local combination is carried out to form a multi-dimensional characteristic vector; the Adaboost algorithm is introduced to carry out characteristic selection; and a classifier is constructed to carry out identification. According to the invention, beneficial effects of the method are as follows: a noise influence is reduced; an identification problem of a low quality iris image can be solved; and the identification performance is good.

Description

technical field [0001] The invention relates to digital image processing and pattern recognition, in particular to an iris recognition method based on multi-directional Gabor and Adaboost, and belongs to the technical field of biological feature recognition and security authentication. Background technique [0002] In modern society, with the rapid development of network technology and the rapid and frequent flow of people, a safe, reliable, convenient and efficient identity authentication system is particularly important. There are two main types of traditional identification: identifying items (keys, ID cards, etc.) and identifying knowledge (usernames, passwords, etc.). However, in practical applications, there are disadvantages such as easy loss, easy forgery, non-uniqueness and relatively small application range, so that people urgently need an identification method that can overcome the above-mentioned defects. Driven by demand, recognition technologies based on biome...

AI Technical Summary

Problems solved by technology

Among them, iris feature extraction is one of the main factors affecting system performance, and most of the existing iris recognition algorithms have high requirements on the quality of iris images

However, iris images collected under natural light will be affected by factors such as eyelashes, eyelids, lighting, shaking, etc., resulting in poor quality of iris images collected. For such low-quality iris images, an effective iris feature extraction and recognition algorithm

Images