Method, device and terminal for determining identity identification of human face in human face image

Abstract

The invention provides a method, device and terminal for determining an identity identification of a human face in a human face image. The method includes the step of obtaining an original characteristic vector of the human face image, selecting k candidate vectors from a human face image database according to the original characteristic vector, choosing a matching vector of the original characteristic vector from the k candidate vectors, and determining an identity identification, recorded in the human face image database, of the matching vector as the identity identification of the human face in the human face image according to the matching vector of the original characteristic vector. According to the method, device and terminal, low-lever human face characteristic vectors and middle-level characteristic vectors formed by interacting with self-correlation and mutual-correlation submatrixes in a combined Bayesian probability matrix are stored in the human face image database, the middle-level characteristic vectors contain characteristic vectors of human faces and information interacting with the self-correlation and mutual-correlation submatrixes in the combined Bayesian probability matrix, and efficiency and accuracy of human face identification can be improved.

Description

technical field [0001] The present invention relates to the communication field, and more specifically, to a method, device and terminal for determining the identity of a human face in a human face image. Background technique [0002] Face recognition is a popular computer technology in recent years, and it is a kind of biometric identification technology. Biometric technology also includes: fingerprint recognition, iris recognition, etc. These recognition technologies can achieve a very high recognition rate. However, the use of these biometric identification technologies requires the cooperation of the identified person, which means that these identification technologies have relatively strict requirements on people and the environment, making these technologies suitable for use in public places, places with a large flow of people, and non-public areas. The application in the mandatory civilian field is greatly restricted. Face recognition can break through the above lim...

AI Technical Summary

Problems solved by technology

[0009] It can be seen from the above that when using the face recognition method based on the joint Bayesian probability model, it is necessary to compare the face feature vector to be matched with all the vectors in the face image database. The scale is relatively large, and using the formula s=[v1,v2]*P*[v1,v2] to compare with each vector in the database requires a lot of calculation and time-consuming, which is not conducive to the rapid recognition of faces

Images