Face image quality evaluation model construction method, face image screening method, face identification method, equipment and medium

Abstract

The invention discloses a face image quality evaluation model construction method, a face image screening method, a face identification method, equipment and a medium. The construction method comprises the following steps that: obtaining a training set, wherein the training set comprises a plurality of face sample images and scoring true values corresponding to the face sample images one by one; according to the face sample images and the scoring true values, training a randomly initialized neural network model; carrying out an accuracy test on the trained neural network model; judging whetherthe result of the accuracy test meets an accurate condition or not; and if the result of the accuracy test meets the accurate condition, storing the trained neural network model as a face image quality evaluation model, wherein the scoring true value is obtained according to the face sample images and the standard image, and the face sample images and the standard image are related. By use of themethod, the constructed face image quality evaluation model can more favorably define face image quality, the subjectivity and the deviation of the manual definition and analysis of face image quality can be avoided, and the method is favorable for screening images in a face identification task.

Description

technical field [0001] The invention relates to the field of image recognition, in particular to a face image quality evaluation model building method, a face image screening method, a face recognition method, electronic equipment and a storage medium. Background technique [0002] Face recognition technology generally compares the captured face image with the pre-stored face photos to determine whether the captured face and the pre-stored face are the same person. At present, face recognition technology has moved from academic research to practical application. For example, face recognition technology is playing an increasingly important role in suspicious person identification and personal identity confirmation. [0003] Whether it is face recognition in the financial field or dynamic face comparison in the security field, face capture images usually come from video streams containing faces. For example, a face recognition system can capture dozens of snapshots of a perso...

AI Technical Summary

Problems solved by technology

Some influencing factors do not have a good quantitative expression method, such as the orientation and angle of the face. The orientation of the face can only be described qualitatively, and the angle of the face cannot be quantitatively measured in the image; for factors that can be quantitatively analyzed, the results are good. Bad only represents one aspect of quality

If each factor is weighted and summed to obtain a quantitative result of the quality, the setting of the weight is very subjective, and there are still deviations in the measurement of the quality of the face, which may not be applicable to the face recognition method based on deep learning.

Images