A method and system for iris location and feature extraction

Abstract

An iris localization and feature extraction method and system are provided in the embodiments of the present application, wherein the steps of the method include: S1. Selecting an iris region segmentation threshold based on a pre-built local grayscale distribution statistical model; S2. Using an iris-based segmentation threshold The double-threshold coupled classifier constructed by the regional segmentation threshold filters the area where the iris is located to obtain the pupil area image and the iris area image; S3. Use the boundary detector constructed based on the pupil area image and the iris area image to determine the effective iris area; S4 . Using the local wavelet high-frequency energy tower transition model constructed based on the effective iris area, the effective iris pixels in the effective iris area are encoded to obtain the iris feature code. This scheme overcomes the influence of noise interference and unstable features in low-quality iris images, thereby improving the accuracy and robustness of the iris recognition system.

Description

technical field [0001] The present application relates to the field of iris biometrics, and in particular to a method and system for precise iris positioning and stable feature extraction based on determining the effective iris area and combining the local wavelet high-frequency energy tower transition model. Background technique [0002] Iris recognition has become a key research direction and development trend in the field of biometrics due to its significant advantages such as accuracy, stability, safety and non-contact. However, due to the small size of the iris, it is susceptible to noise interference, and the influence of the user's posture. In the collected iris image, the iris area often has pollution and deformation. Therefore, how to solve the problem of precise iris positioning and stable feature extraction in low-quality images, It is the key and difficulty of iris recognition. The current typical iris feature extraction and matching methods have the following s...

AI Technical Summary

Problems solved by technology

[0003] 1. There is a lack of adaptable iris positioning fitting model. For low-quality images, iris positioning is greatly affected by noise interference, and the positioning is inaccurate, which makes the extraction of iris stable features more difficult;

[0004] 2. There is a lack of robust iris feature measurement operators. For low-quality images, feature extraction is greatly affected by iris deformation, and it is difficult to extract stable iris features, which greatly reduces the accuracy of iris recognition;

[0005] 3. For low-quality images, in order to avoid the decline in the accuracy of iris recognition, a strategy of discarding the current image for re-acquisition is adopted, which seriously affects the efficiency of the iris recognition system

Images