Multi-Biological Feature Fusion Recognition Method Based on Image Quality Assessment

Abstract

The present invention is a multi-biological feature fusion recognition method based on image quality assessment. Firstly, the user's face and iris images are collected through the image collection subsystem and correspondingly preprocessed, and secondly, the preprocessed images are respectively sent to corresponding The identification and authentication subsystem of the identification and authentication subsystem performs steps such as quality assessment, feature extraction, and template matching, and outputs respective matching scores and corresponding matching quality confidence scores. Finally, these scores are normalized and sent to the identification and fusion subsystem, and the dynamic weighted fusion algorithm is used to obtain Identify the authentication result. The beneficial effect of the present invention is that: the method has higher recognition accuracy than a single face or iris recognition algorithm, and can realize high-precision personal identification; at the same time, the method is based on the existing mainstream fusion recognition algorithm. On the other hand, the useful information of image quality is extracted and applied to the fusion identification and authentication process to further improve the system identification performance.

Description

technical field [0001] Embodiments of the present invention relate to a multi-biometrics fusion recognition method based on image quality assessment, and more particularly, to a multi-biometrics fusion recognition method based on image quality assessment including face recognition and iris recognition. Background technique [0002] With the rapid development of informatization construction, the growing physical and virtual activity spaces of human beings face more and more problems of identity authentication and identification. The traditional authentication and identification methods based on ID cards or passwords have the risk of being easily forgotten and stolen. What is particularly serious is that these traditional methods cannot distinguish the real owner from the impostor who obtains the identity identifier, and use a person's inherent physiological or behavioral characteristics to achieve identity authentication and identification, and some inherent attributes of biom...

AI Technical Summary

Problems solved by technology

However, this type of algorithm does not make full use of the useful information of the image, which limits the performance improvement of fusion recognition.

Images