Open AccessEmotiongan: Facial Expression Synthesis Based on Pre-Trained Generator
Author(s) -
Xin Ning,
Shaohui Xu,
Yixin Zong,
Weijuan Tian,
Linjun Sun,
Xianlin Dong
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1518/1/012031
Subject(s) - discriminator , generator (circuit theory) , expression (computer science) , feature vector , computer science , feature (linguistics) , facial expression , artificial intelligence , pattern recognition (psychology) , face (sociological concept) , image (mathematics) , minimax , identity (music) , computer vision , mathematics , mathematical optimization , power (physics) , telecommunications , social science , linguistics , physics , philosophy , quantum mechanics , detector , sociology , programming language , acoustics
Since the Generative Adversarial Networks (GANs) was proposed, researches on image generation attract many scholars’ general attention and good graces. Traditional GANs generate a sample by playing a minimax game between generator and discriminator. In this paper, we propose a new method called EmotionGAN for generating facial expression. Specifically, the inverse of the generator is firstly utilized to establish the mapping between the input and feature vector. Then the Generalized Linear Model (GLM) is used to fit the changing direction of different expressions in the feature space, which provide a linear guidance to the feature vector along the expression axis, and thus spatial distribution consistence with the target feature vector is assured. Finally the generator is applied to reconstruct the facial image of the expression. By controlling the intensity of the feature vector, the generated image can be smoothly changed on a specific expression. Experiments have shown that EmotionGAN can quickly generate face images with arbitrary expressions while ensuring identity information is not changed, and the image attributes are more accurate and the resolution is higher.