Face transfer method capable of maintaining expression information based on CNN

Abstract

The invention discloses a face transfer method capable of maintaining expression information based on CNN. The method achieves the face conversion effect of saving the feature information by combiningthe face recognition network and the expression recognition network, and may transfer the face of a picture A to the face of another picture B, and the expression information of the picture B and therest of the non-face information are still maintained during the conversion process. The invention solves two core technical problems that: the problem that the synthesized part is not in harmony with the original part in the process of face synthesis, and the problem of missing face information after the synthesis part and the original part are synthesized, including the lost of identification information and the expression information. By implementing the embodiments of the invention, the demand for image processing in people's lives may be increased, so that the face processing may be applied in various ways. At the same time, the "photographing unsuitable people" may generate more own images by means of image synthesis.

Description

technical field [0001] The invention relates to the fields of computer vision and artificial intelligence, in particular to a CNN-based face transfer method for maintaining expression information. Background technique [0002] In the 1980s, Hinton, Rumelhart and others established and promoted the back-propagation algorithm (back-propagation) used to train multi-layer neural networks, and the neural network ushered in the spring again. Through the back-propagation algorithm, people can further improve the computer's learning process to a level beyond the reach of previous learning algorithms after a huge amount of calculations by the computer. Deep Learning is a concept proposed by Professor Geoffrey Hinton of the University of Toronto. Because the traditional multi-layer perceptron is easy to fall into the local minimum, the classification effect directly obtained by the back propagation algorithm (Back Propagation) is not satisfactory. The first reason is that the feature...

AI Technical Summary

Problems solved by technology

The present invention solves two core technical problems, one is the disharmony between the synthetic part and the original image part in the process of human face synthesis; the second is the loss of face information after the synthetic part and the original image part are synthesized, including identification information and expression information is lost

Images