Non-contact revocable palm print bimodal authentication method

Abstract

The invention discloses a non-contact revocable palm print bimodal authentication method. A non-contact device is used for collection a palm print. Point set operation is adopted for preprocessing. A Gabor filter is adopted for extracting texture features. Random projection and quantization are conducted on the texture features and a random matrix with the participation of external variable parameters. A revocable template of a 2DPalmHash code is generated, and the generation direction of the revocable template is optimized according to a low correlation policy. During registration, the template of the bimodal 2DPalmHash code is stored in a database; during authentication, the template is extracted from the database and contrasted with authentication templates one by one, fractional order integration is conducted, and revocable palm print authentication is realized. According to the non-contact revocable palm print bimodal authentication method, the accuracy of the template is improved as the point set operation is adopted; the revocable template is given updating capacity; the feature template is optimized according to a proper strategy, and authentication precision is improved without increasing time and space complexity.

Description

technical field [0001] The invention relates to a biometric authentication method, in particular to a non-contact revocable dual-mode authentication method of palm prints and veins. Background technique [0002] When the contact palmprint and palm vein collection device is used for a long time, it is easy to cause surface pollution of the equipment, resulting in problems such as reduced accuracy and hidden health hazards. Although non-contact collection overcomes the above defects, the preprocessing process of palm prints and palm veins is easily disturbed by more factors, such as complex background and lighting conditions in natural scenes; the unfixed palm position makes the shooting distance, angle and The amount of rotation is not uniform; the posture of the palm (such as fingers close together, open, etc.) is not uniform. Therefore, it is necessary to design a higher-precision preprocessing algorithm to improve the positioning accuracy. [0003] Existing palmprint and...

AI Technical Summary

Problems solved by technology

[0003] Existing palmprint and palm vein authentication systems use original feature templates, which have many security and privacy issues: when a feature is stolen, it cannot be revoked or updated; with the promotion of the application range, multiple databases may store the same feature template, If the feature templates in the low security level database are stolen, all the feature templates in other databases will be invalid; the original features may leak the user's private information (such as genetic defects, diseases, etc.)

Images