Model training method, face recognition method, electronic equipment and storage medium

Abstract

The embodiment of the invention relates to the field of image processing, and discloses a model training method, a face recognition method, electronic equipment and a storage medium, and the model training method comprises the steps: obtaining an infrared image sample of a face and the label data of the infrared image sample; inputting the infrared image samples into a feature extraction network to obtain feature images of different sizes; inputting the feature maps of different sizes into a feature fusion network to obtain a feature fusion map; inputting the feature fusion image into an output network to obtain prediction data; and training a joint network model composed of the feature extraction network, the feature fusion network and the output network based on a first loss function constructed by the label data and the prediction data to obtain the trained joint network model. According to the scheme, the face recognition model is trained by adopting the infrared image with relatively high quality, so that the face recognition rate is improved.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a model training, a face recognition method, electronic equipment and a storage medium. Background technique [0002] At present, face recognition technology has been widely used in various electronic systems, such as access control systems, bayonet systems, electronic passports, public security, bank self-service systems, information security, etc. However, in the process of face recognition, misrecognition is easy to occur, and it cannot be applied to the situation without light. How to improve the recognition rate is particularly important. [0003] The face quality evaluation of the existing face detection technology mostly uses the angle, clarity, illumination contrast, eye state, mouth state, etc. of the color face image for quality evaluation in order to improve the accuracy of subsequent face recognition. The problem with this method is that situations such as zero light ...

AI Technical Summary

Problems solved by technology

The problem with this method is that situations such as zero light or strong light, and normal wearing of masks are considered to be of low quality and cannot be sent to subsequent face recognition, and cannot be applied in dark nights and scenes wearing masks.

Images