CN-121747231-B - User release method, device, computer equipment and storage medium

CN121747231BCN 121747231 BCN121747231 BCN 121747231BCN-121747231-B

Abstract

The application relates to a user release method, a user release device, computer equipment and a storage medium. The method comprises the steps of obtaining a first fingerprint image, a first face image and a first voice signal of a first user, determining quality scores of the first fingerprint image, the first face image and the first voice signal respectively to determine a first weight of the first fingerprint image, a second weight of the first face image and a third weight of the first voice signal respectively, determining a first similarity between the first fingerprint image and a second fingerprint image of a second user, a second similarity between the first face image and a second face image of the second user and a third similarity between the first voice signal and a second voice signal of the second user respectively, and determining a release result for the first user based on the first weight, the first similarity, the second weight, the second similarity, the third weight and the third similarity. By adopting the method, the authentication accuracy aiming at the first user can be improved.

Inventors

LIU GUOPING
CHEN XIAOMING
Liu Qunwei
YI JINHONG

Assignees

深圳市乔安科技有限公司
东莞市乔安智联科技有限公司

Dates

Publication Date: 20260508
Application Date: 20260228

Claims (10)

1. A user release method, comprising: The method comprises the steps of acquiring a first fingerprint image, a first face image and a first voice signal of a first user, wherein first image parameters of the first fingerprint image comprise definition, ridge line integrity and effective area proportion of the first fingerprint image, second image parameters of the first face image comprise illumination balance degree, shielding rate and key point confidence coefficient of the first face image, and voice parameters of the first voice signal comprise signal-to-noise ratio and voice effective duration of the first voice signal; determining a quality score of the first fingerprint image, the first face image and the first speech signal, respectively; Determining a first weight of the first fingerprint image, a second weight of the first face image, and a third weight of the first speech signal, respectively, based on the quality scores of the first fingerprint image, the first face image, and the first speech signal; Determining a first similarity between the first fingerprint image and a second fingerprint image of a second user, a second similarity between the first face image and a second face image of the second user, and a third similarity between the first speech signal and a second speech signal of a second user, the second user being any stored user, respectively; Determining a release result for the first user based on the first weight, the first similarity, the second weight, the second similarity, the third weight, and the third similarity; Wherein the determining the quality scores of the first fingerprint image, the first face image, and the first voice signal, respectively, comprises: determining a quality score of the first fingerprint image based on a first image parameter of the first fingerprint image; determining a quality score of the first facial image based on a second image parameter of the first facial image; determining a quality score of the first speech signal based on a speech parameter of the first speech signal; the determining the quality score of the first fingerprint image based on the first image parameter of the first fingerprint image includes: Determining a quality fraction of the first fingerprint image based on the definition, the ridge line integrity and the effective area proportion of the first fingerprint image, wherein the quality fraction of the first fingerprint image and the definition, the ridge line integrity and the effective area proportion of the first fingerprint image are respectively in positive correlation; the determining the quality score of the first face image based on the second image parameters of the first face image includes: Determining a quality score of the first face image based on the illumination balance degree, the shielding rate and the key point confidence degree of the first face image, wherein the quality score of the first face image, the illumination balance degree and the key point confidence degree of the first face image respectively show positive correlation, and the quality score of the first face image and the shielding rate show negative correlation; the determining a quality score of the first speech signal based on the speech parameters of the first speech signal comprises: And determining the quality score of the first voice signal based on the signal-to-noise ratio and the voice effective duration of the first voice signal, wherein the quality score of the first voice signal, the signal-to-noise ratio and the voice effective duration of the first voice signal are respectively in positive correlation.
2. The method of claim 1, wherein the acquiring the first fingerprint image, the first face image, and the first voice signal of the first user comprises: The method comprises the steps of obtaining a first fingerprint image of a first user through a fingerprint sensor, obtaining a first face image of the first user through a camera, and obtaining a first voice signal of the first user through a microphone.
3. The method of claim 1, wherein a sum between the first weight, the second weight, and the third weight is 1.
4. The method according to claim 1, wherein the method further comprises: And when the quality score of the first fingerprint image is smaller than a first score threshold, the quality score of the first face image is smaller than a second score threshold or the quality score of the first voice signal is smaller than a third score threshold, the steps of acquiring the first fingerprint image, the first face image and the first voice signal of the first user and respectively determining the quality scores of the first fingerprint image, the first face image and the first voice signal are executed.
5. The method of claim 2, wherein the determining the quality score of the first fingerprint image based on the first image parameter of the first fingerprint image comprises: Determining the quality fraction of the first fingerprint image based on a first image parameter of the first fingerprint image and the pollution degree of a fingerprint sensor used for acquiring the first fingerprint image, wherein the quality fraction of the first fingerprint image and the pollution degree of the fingerprint sensor are in a negative correlation; the determining a quality score of the first face image based on a second image parameter of the first face image includes; Determining a quality score of the first face image based on a second image parameter of the first face image and a brightness value of the first face image, wherein the quality score of the first face image and the brightness value of the first face image are in positive correlation; the determining a quality score of the first speech signal based on the speech parameters of the first speech signal comprises: And determining the quality score of the first voice signal based on the voice parameter of the first voice signal and the environmental noise index of the first voice signal, wherein the quality score of the first voice signal and the environmental noise index of the first voice signal are in a negative correlation relationship.
6. The method of claim 1, wherein the determining a release result for the first user based on the first weight, the first similarity, the second weight, the second similarity, the third weight, and the third similarity comprises: Based on the first weight, the second weight and the third weight, carrying out weighted summation on the first similarity, the second similarity and the third similarity to obtain fusion similarity; And determining to pass the first user under the condition that the fusion similarity is greater than or equal to a first similarity threshold.
7. The method of claim 6, wherein the method further comprises: The first similarity threshold is determined based on a preset reference value, the abnormal degree of the passing behavior of the first user and the safety level of a monitoring area, wherein the first similarity threshold is in positive correlation with the abnormal degree of the passing behavior of the first user and the safety level of the monitoring area respectively under the condition that the preset reference value is kept unchanged, and the monitoring area is the area for acquiring the first face image.
8. A user release apparatus, comprising: the system comprises an acquisition module, a voice acquisition module and a voice acquisition module, wherein the acquisition module is used for acquiring a first fingerprint image, a first face image and a first voice signal of a first user, wherein first image parameters of the first fingerprint image comprise definition, ridge line integrity and effective area proportion of the first fingerprint image, second image parameters of the first face image comprise illumination balance degree, shielding rate and key point confidence degree of the first face image, and voice parameters of the first voice signal comprise signal-to-noise ratio and voice effective duration of the first voice signal; A first determining module, configured to determine quality scores of the first fingerprint image, the first face image, and the first voice signal, respectively; A second determining module, configured to determine a first weight of the first fingerprint image, a second weight of the first face image, and a third weight of the first speech signal, respectively, based on the quality scores of the first fingerprint image, the first face image, and the first speech signal; a third determining module, configured to determine a first similarity between the first fingerprint image and a second fingerprint image of a second user, a second similarity between the first face image and a second face image of the second user, and a third similarity between the first speech signal and a second speech signal of the second user, where the second user is any stored user; a fourth determining module, configured to determine a release result for the first user based on the first weight, the first similarity, the second weight, the second similarity, the third weight, and the third similarity; The first determining module is specifically configured to determine a quality score of the first fingerprint image based on a first image parameter of the first fingerprint image, determine a quality score of the first face image based on a second image parameter of the first face image, and determine a quality score of the first voice signal based on a voice parameter of the first voice signal; The voice signal quality control method comprises the steps of determining a quality score of a first fingerprint image based on first image parameters of the first fingerprint image, determining the quality score of the first fingerprint image based on definition, ridge line integrity and effective area proportion of the first fingerprint image, wherein the quality score of the first fingerprint image is in positive correlation with the definition, ridge line integrity and effective area proportion of the first fingerprint image respectively, determining the quality score of the first face image based on second image parameters of the first face image, determining the quality score of the first face image based on light balance degree, shielding rate and key point confidence coefficient of the first face image, wherein the quality score of the first face image is in positive correlation with the light balance degree and the key point confidence coefficient of the first face image respectively, determining the quality score of the first voice signal based on voice parameters of the first voice signal, determining the quality score of the first voice signal based on the first face image is in negative correlation with the shielding rate, and the voice signal quality control method comprises the voice signal quality control method based on the first face image parameters, and determining the voice signal quality control method based on the first face signal quality score and the first voice signal quality has positive correlation time.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.

Description

User release method, device, computer equipment and storage medium Technical Field The present application relates to the field of data processing technologies, and in particular, to a user release method, a device, a computer device, and a storage medium. Background Along with the rapid improvement of the living standard of people, the entrance guard safety problem is also paid attention to gradually. In the traditional internet of things equipment, a single fingerprint image or single face information is generally adopted to verify the identity of a visitor, and if the information to be verified has singleness, the information to be verified can be easily forged and wrongly released. Disclosure of Invention In view of the foregoing, it is desirable to provide a user release method, apparatus, computer device, computer readable storage medium, and computer program product that can improve the accuracy of authentication for a first user. In a first aspect, the present application provides a user release method, including: acquiring a first fingerprint image, a first face image and a first voice signal of a first user; Respectively determining the quality scores of the first fingerprint image, the first face image and the first voice signal; determining a first weight of the first fingerprint image, a second weight of the first face image, and a third weight of the first speech signal, respectively, based on the first fingerprint image, the first face image, and the quality score of the first speech signal; Respectively determining a first similarity between a first fingerprint image and a second fingerprint image of a second user, a second similarity between the first face image and a second face image of the second user, and a third similarity between a first voice signal and a second voice signal of the second user, wherein the second user is any stored user; and determining a release result for the first user based on the first weight, the first similarity, the second weight, the second similarity, the third weight, and the third similarity. In a second aspect, the present application also provides a user release device, including: The acquisition module is used for acquiring a first fingerprint image, a first face image and a first voice signal of a first user; the first determining module is used for respectively determining the quality scores of the first fingerprint image, the first face image and the first voice signal; The second determining module is used for respectively determining a first weight of the first fingerprint image, a second weight of the first face image and a third weight of the first voice signal based on the quality scores of the first fingerprint image, the first face image and the first voice signal; A third determining module, configured to determine a first similarity between the first fingerprint image and a second fingerprint image of a second user, a second similarity between the first face image and a second face image of the second user, and a third similarity between the first speech signal and a second speech signal of the second user, where the second user is any stored user; And the fourth determining module is used for determining a release result for the first user based on the first weight, the first similarity, the second weight, the second similarity, the third weight and the third similarity. In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing some or all of the steps described in any of the methods of the first aspect of the embodiments of the present application when the processor executes the computer program. In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium has stored thereon a computer program which when executed by a processor implements some or all of the steps described in any of the methods of the first aspect of the embodiments of the present application. In a fifth aspect, the present application also provides a computer program product. The computer program product comprising a computer program which, when executed by a processor, implements some or all of the steps described in any of the methods of the first aspect of the embodiments of the application. The above user release method, apparatus, computer device, computer readable storage medium and computer program product determine a first weight of a first fingerprint image, a second weight of the first face image and a third weight of a first speech signal, respectively, based on the quality scores of the first fingerprint image, the first face image and the first speech signal, by acquiring the first fingerprint image, the first face image and the first speech signal of the first user, and determining a second similarity between the first fingerprint image and the second face image of the second u