Multi-mode biological feature fusion device

Abstract

The invention discloses a multi-modal biological feature fusion device. The device comprises a biological characteristic acquisition unit, a characteristic parameter extraction unit, a parameter normalization processing unit, a characteristic parameter fusion unit and a biological characteristic recognition unit. Compared with the prior art, the beneficial effects of the invention are that by obtaining the five biological characteristics, ten groups of combined biological characteristics can be combined, and by recognizeing any group of biological characteristics, the verification of a singlebiological characteristic is avoided, the recognition safety and accuracy are improved, the identity recognition failure caused by the fact that part of the biological characteristics are damaged andcannot be recognized, can be prevented, and more choices are provided for the identity recognition; after the fingerprint is collected, the fingerprint is removed by the adhesive surface of a transparent adhesive tape, so that the surface layer of a fingerprint sensor has no fingerprint mark, the indirect infection of the onychomycosis is prevented, the cleanliness of the surface layer of the fingerprint sensor can be ensured, the next fingerprint collection is facilitated, and the accuracy of fingerprint collection and recognition is improved.

Description

technical field [0001] The invention relates to the technical field of biometric feature recognition, in particular to a multimodal biometric feature fusion device. Background technique [0002] Biometric identification technology is the most convenient and safe technology for personal identification through face features, fingerprint features, vein features, palmprint features, voiceprint features and even iris features, and is easy to cooperate with computers and security and monitoring , management system integration, and automatic management, which are widely used. However, with the emergence of high-tech means such as simulated headgear, holographic projection, and face tracking, the method of using a single biometric feature for identification and authentication is inaccurate and safe. The sensitivity has been greatly reduced, so multimodality is an inevitable trend of biometrics. [0003] The current multi-modal biometric technology is fused by acquiring two or more ...

AI Technical Summary

Problems solved by technology

[0002] Biometric identification technology is the most convenient and safe technology for personal identification through face features, fingerprint features, vein features, palmprint features, voiceprint features and even iris features, and is easy to cooperate with computers and security and monitoring , management system integration, and automatic management, which are widely used. However, with the emergence of high-tech means such as simulated headgear, holographic projection, and face tracking, the method of using a single biometric feature for identification and authentication is inaccurate and safe. The accuracy has been greatly reduced, so multi-modality is an inevitable trend of biometrics

[0003] The current multi-modal biometric technology is fused by acquiring two or more biometric features, so that when verifying, only two or more biometric features obtained can be used for identification and verification. If two or more biometric features One of the features is damaged, which will lead to the failure of the total identity verification, such as successful fingerprint recognition, but the facial feature recognition fails due to changes in the face due to makeup, injury, etc., so the identity verification fails. Certain limitations;

[0004] In addition, among biometric features, fingerprint features are the most widely used, so the probability of fingerprint feature identification will be higher than other biometric features. Because the finger needs to be in contact with the surface of the fingerprint sensor during fingerprint collection, it will cause the fingerprint to be printed on the surface of the fingerprint sensor. If there is onychomycosis, it will lead to indirect infection, and the residual fingerprints will affect the subsequent fingerprint collection to a certain extent, which will greatly reduce the accuracy of fingerprint collection, resulting in the failure of fingerprint recognition or repeated fingerprint collection

Images