Wavelet packet decomposition-based iris feature extraction and matching method

Abstract

The invention discloses an iris feature extraction and matching method. The method comprises the steps of performing block segmentation and denoising processing on a standard iris image, and performing iris feature extraction on all denoised sub-blocks to form a feature template; performing one-layer wavelet packet decomposition on each sub-block image, extracting a radial texture feature and an arc texture feature of an iris, and forming a circumferential eigenvector; performing multi-layer wavelet packet decomposition on each sub-block image, extracting a global energy distribution feature and a local energy distribution feature of the iris, and forming an energy eigenvector; forming an iris eigenvector of each sub-block image by the circumferential eigenvector and the energy eigenvector of each sub-block, and forming the feature template of the iris image by the iris eigenvectors of the sub-block images; and performing matching identification on feature templates of two iris images, and gradually performing judgment classification based on similarity and a Hamming distance. According to the scheme, the real-time property and adaptability of iris feature extraction and matching can be effectively improved on the basis of ensuring identification precision.

Description

technical field [0001] The invention relates to the field of iris image processing and identification, in particular to an iris feature extraction method used in an iris biometric identification system. Background technique [0002] Iris recognition has significant advantages such as accuracy, stability, security and practicability. It is the most advanced biometric technology known at present and has a broad market prospect. In the actual iris recognition system, iris feature extraction and matching are the core links of iris recognition. Only by extracting as many stable and independent feature point information as possible, and adopting a reasonable classification and discrimination strategy, while taking into account the adaptability of the algorithm, Reducing the requirements for iris image acquisition and preprocessing can effectively improve the performance of the iris recognition application system, taking into account the accuracy and speed of recognition. [0003]...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide an iris feature extraction and matching method based on wavelet packet decomposition, which solves the problem of poor real-time and adaptability of iris feature extraction and matching on the basis of ensuring recognition accuracy

Images