Face recognition image processing method and system

Abstract

The invention discloses a face recognition image processing method, which comprises the following steps: obtaining an identity card face photo of a person to be recognized with time parameters and a real-time face image with time parameters and environmental parameters at the same time; extracting human face features in the identity card human face photo with time parameters and human face features in the real-time human face image with time parameters and environmental parameters; calculating an identity card face feature autocorrelation coefficient, and at least adding a time parameter function to the identity card face feature autocorrelation coefficient to serve as a specific use condition; calculating an on-site face feature autocorrelation coefficient according to face features in the real-time face image, and at least adding a time parameter function and an environment parameter function to the on-site face feature autocorrelation coefficient to serve as specific use conditionsof the on-site face feature autocorrelation coefficient; and identifying the identity of the person to be identified according to the identity card face feature autocorrelation coefficient and the on-site face feature autocorrelation coefficient. The invention further discloses a system corresponding to the method.

Description

technical field [0001] The invention relates to a face recognition image processing method and system. Background technique [0002] Chinese invention patent CN201710139212.1 discloses a face recognition processing method and system. In this patent technology, there are defects in face recognition based on joint Bayesian, that is, two photos assumed to be input in face recognition (Associated objects to be identified) are symmetrical and identically distributed, so ID card face recognition cannot be fully utilized. Therefore, the above-mentioned technology uses different distribution face recognition between ID card chip face photos and on-site real-time face images. It is confirmed that multiple covariance matrix parameters are calculated by training a large number of face photos, and at the same time, the parameters are obtained by using high-definition ID card photos to assist training, which improves the accuracy of recognition and scene adaptability. In its specific imp...

AI Technical Summary

Problems solved by technology

[0023] However, in practical applications, the problem that needs to be paid attention to is that although the face photos collected on the spot often have high resolution, the illumination, posture, and expression changes are large and due to the uncertainty of illumination, posture, and expression changes, so simple Relying on the sample data collected on-site is not enough to support the recognition accuracy. In addition, for face recognition photos, the on-site collection time is usually about 0-10 years later than the ID card photo collection time, but in fact, according to the changes in human facial features According to the law and the validity period of various ID documents, people of different age groups have different degrees of difference between their ID card photos or their high-definition photos with a certain shooting time and the face photos collected on the spot. In other words, people of different age groups There should be specific and regular differences between the crowd, their ID card photos or their high-definition photos with a certain shooting time and the face photos collected on the spot. direction of research

Images