Latent semantic feature extraction method in aged user multi-biometric identity authentication

Abstract

The invention relates to a latent semantic feature extraction method in aged user multi-biometric identity authentication. Identity authentication is performed by performing multi-mode latent semantic analysis and data mining mapping on aged user multi-biometric images and extracting the latent semantic features of the images. According to the latent semantic feature extraction method in the ageduser multi-biometric identity authentication, multiple local bottom features can be acquired by extracting the multi-biometric images of face, multiple fingerprints and palm prints and the like; the extracted features can be processed by using a multi-mode latent semantic analysis algorithm on three aspects of bottom feature-image matrix construction, two-dimensional matrix decomposition and clustering algorithm; the processed features are further mined and mapped through an 'intelligent black box model', so that the latent semantic features of the images can be effectively acquired; and the system is automatically adjusted by introducing an adaptive feedback structure with a genetic algorithm (GA), so that modification of the latent semantic features of the images is realized.

Description

technical field [0001] The invention relates to the technical field of biometric identification, in particular to an implicit semantic feature extraction method in multi-biological feature identity authentication of elderly users. Background technique [0002] At present, the population over 60 years old in my country has reached 180 million, accounting for about 13.8% of the total population. According to international standards, my country has entered an aging society. As the country vigorously accelerates the establishment and improvement of a social security system covering urban and rural residents, such as social In the distribution of pension insurance, enterprise annuity, medical insurance, etc., elderly users will become the main group of social public services in the future. The phenomenon of deception and false claims in the distribution process of social pension insurance and enterprise annuity has become a common concern in today's society. Informatization, digita...

AI Technical Summary

Problems solved by technology

The "Technical Specifications for Pension Payment Fingerprint Identity Authentication System (Trial)" issued by the Social Insurance Management Center of the Ministry of Labor and Social Security of my country will also promulgate the fingerprint identification method based on minutiae as a social public service standard. For elderly users, blurred fingers are very common due to weathering. The traditional minutiae-based fingerprint recognition system often leads to an increase in the false recognition rate of the system and even invalidation of authentication due to unsatisfactory extraction of minutiae points.

In addition, the recognition technology based on a single biological feature is not universal: some biological features are missing (such as a broken finger), damage (such as a damaged finger), lesions (such as cataracts) or poor quality of feature collection (such as facial light Changes) will lead to poor robustness and reliability of the recognition system, weak anti-spoofing, and it is difficult to meet the actual requirements of different occasions

Images