Face image recognition method, device and equipment and computer readable storage medium

Abstract

The embodiment of the invention discloses a face image recognition method, device and equipment and a computer readable storage medium. According to the embodiment of the invention, the method includes connecting a plurality of face image samples of a target object and an image score corresponding to each face image sample; selecting a face image sample pair from the face image samples according to the difference value between the image scores, wherein the face image sample pair comprises a first face image and a second face image, and the image score of the first face image is larger than that of the second face image; performing joint training on a preset model according to the face image sample pair and the corresponding image score to obtain a trained target model, the target model being obtained by performing distillation training on a difference between a first feature parameter corresponding to the first face image and a second feature parameter corresponding to the second face image; and performing face recognition on the to-be-recognized face image through the target model. In this way, the recognition rate of low-quality face images can be increased, and the accuracy of face recognition is improved.

Description

technical field [0001] The present application relates to the field of artificial intelligence, in particular to a face image recognition method, device, equipment and computer-readable storage medium. Background technique [0002] With the development of information security technology, when people face login or authentication scenarios, they can use face image recognition technology for information authentication to achieve fast information authentication. However, in the face image recognition process, due to the low quality of the collected face images, the face image recognition may fail. In order to improve the recognition rate of face images, related technologies obtain the uncertainty of all features in the face image, suppress the expression of features with high uncertainty, and strengthen the weight of features with low uncertainty, that is, strengthen the weight of features with low uncertainty. Features are expressed for face image recognition. [0003] During...

AI Technical Summary

Problems solved by technology

[0003] During the research and practice of the prior art, the inventors of the present application found that for the existing face image recognition, it relies on a sufficient number of low-uncertainty features in the face image. When the number of features with low uncertainty in the image is small, it is impossible to recognize low-quality face images, which leads to a low recognition rate of face images, which affects the accuracy of face recognition

Images