Face recognition model construction method and device, computer equipment and storage medium

Abstract

The invention relates to a face recognition model construction method for face recognition, and the method comprises the steps: obtaining a plurality of pieces of sample image data, carrying out the feature extraction of the sample image data through a feature extraction model, and obtaining race face features corresponding to a plurality of race identifications; determining race face feature setscorresponding to the race identifiers according to the race face features, and training by using the race face feature sets to obtain an initial face generation model; verifying the initial face generation model, and obtaining a required face generation model after the verification is passed; synthesizing race face synthesis images corresponding to the race identifiers by utilizing a face generation model; extracting face features of the race face synthesis image and adding the face features into a race face feature set; and training and verifying the initial face recognition model by using the race face feature set to obtain a required face recognition model. By adopting the method, the face recognition model with relatively high race face recognition accuracy can be effectively generated, so that the face recognition accuracy is effectively improved.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a face recognition model construction method, device, computer equipment and storage medium for face recognition. Background technique [0002] With the rapid development of computer technology, face recognition technology continues to mature. Generative confrontation model is one of the important breakthroughs of artificial intelligence in recent years, and has attracted widespread attention from all walks of life. Training a generative confrontation model also requires huge computing power and a large amount of data. A generative confrontation model trained based on a single independent task cannot be directly used for other tasks. [0003] In the existing methods, the data sources for model training are usually limited by using a large amount of face image data, such as face images limited to a specific area, and the data types of the training data set are unbalan...

AI Technical Summary

Problems solved by technology

Training a generative confrontation model also requires huge computing power and a large amount of data. A generative confrontation model trained based on a single independent task cannot be directly used for other tasks

[0003] In the existing methods, the data sources for model training are usually limited by using a large amount of face image data, such as face images limited to a specific area, and the data types of the training data set are unbalanced, so that the trained model is suitable for different types. The recognition accuracy rate is not high

Images