Facial avatar cartoonization realization method based on cyclic generative adversarial nets

Abstract

The invention discloses a facial avatar cartoonization realization method based on cyclic generative adversarial nets. The method includes the steps of crawling a number of real people pictures and cartoon character pictures from the network; identifying the face in the pictures based on the face detection algorithm to obtain a real face avatar and a cartoon face avatar as training samples; constructing cyclic generative adversarial nets composed of generators and discriminators and designing a loss function; taking the real face avatar and the cartoon face avatar as the input, training the cyclic generative adversarial nets to minimize the loss function; and inputting the real face avatar to be processed into the generators of the trained cyclic generative adversarial nets to obtain the corresponding cartoon face avatar. The performance of the first generator of the cyclic generative adversarial nets can be optimal, the input real face avatar can be cartoonized, and the real-timenessand effectiveness of face cartoonization can be realized.

Description

technical field [0001] The invention relates to a method for realizing cartoonization of human faces and head portraits based on cyclic generation confrontation network, and belongs to the technical field of image processing in computer vision. Background technique [0002] In recent years, with the rise of artificial intelligence, deep learning has received extensive attention, and the proposal of generative adversarial networks has accelerated the process of deep learning. In 2014, scholars such as Ian Goodfellow of the University of Montreal proposed the concept of "generative confrontation network", which gradually attracted the attention of AI professionals. Since 2016, there has been a "blowout" of academic and industry interest in GANs: [0003] A number of heavyweight papers have been published one after another; AI industry giants such as Facebook and OpenAI have also joined the research on GANs; it has become a well-deserved star at the NIPS conference in December...

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is to overcome the deficiencies of the prior art, provide a method for realizing the cartoonization of human faces and avatars based on cyclic generative confrontation network, and solve the problems of poor transformation effect and some good effects but slow speed in traditional methods , so that the real-time and effectiveness of face cartoonization

Images