Fully convolutional neural network-based screening face image identification method and device

Abstract

The invention discloses a fully convolutional neural network-based screening face image identification method and device. The method includes the following steps that: screening face images and corresponding clear face images which form image pairs are collected, and the image pairs are utilized train a fully convolutional neural network which is used for restoring a clear face image from a screening image, namely performing de-screening; and when identification is carried out, a screening face image is inputted into a trained de-screening model, so that a clear face image can be obtained so as to be used for performing a subsequent face identification task. According to the method and device of the invention, the fully convolutional neural network is adopted as the main body of a learning frame, so that the characteristics of larger visual receptive field and faster computing speed of the fully convolutional neural network can be utilized; and according to the design of the training of a target function, pixel-level reconstruction loss and face feature-level reconstruction loss are combined, a spatial transformation module is used in a matched manner to perform precise perfect alignment on face regions in the network so as to realize the accurate extraction of the features of the face regions. With the method of the invention adopted, the clear face image can be restored from the screening image, face features can be kept relatively stable during a restoration process, and therefore, the identification accuracy of the screening face image can be greatly improved.

Description

technical field [0001] The present invention relates to computer vision, pattern recognition, machine learning and other technical fields, in particular to a fully convolutional neural network-based meshed face image recognition method and device (Fully Convolutional Network for DeepMeshFace Verification, DeMeshNet for short). Background technique [0002] Due to its non-contact identity authentication method and its accurate and convenient features, face recognition technology has begun to receive attention in all aspects of our lives. Not only is it widely used in traditional airport security checks, face time attendance, and customs clearance, but face recognition technology is also gradually being widely used in the mobile Internet. In particular, the face recognition technology based on the comparison of ID photos and life photos has begun to be greatly promoted in the field of Internet finance. The remote bank account opening and wallet payment functions based on this ...

AI Technical Summary

Problems solved by technology

Although the existence of these textures protects user privacy to a certain extent, it has caused huge interference to the automatic face recognition system and seriously reduced the accuracy of face recognition.

Images