Learning to represent 2D human face with mathematical model

作     者：Liping Zhang Weijun Li Linjun Sun Lina Yu Xin Ning Xiaoli Dong 

作者机构：AnnLabInstitute of SemiconductorsChinese Academy of SciencesBeijingChina Center of Materials Science and Optoelectronics EngineeringSchool of Integrated CircuitsUniversity of Chinese Academy of SciencesBeijingChina Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing TechnologyBeijingChina 

出 版 物：《CAAI Transactions on Intelligence Technology》 (智能技术学报（英文）)

年 卷 期：2024年第9卷第1期

页      面：54-68页

核心收录：

学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 

基　　金：National Natural Science Foundation of China Grant/Award Number:92370117 

主　　题：artificial neural networks face analysis image processing mathematics computing 

摘      要：How to represent a human face pattern?While it is presented in a continuous way in human visual system,computers often store and process it in a discrete manner with 2D arrays of *** authors attempt to learn a continuous surface representation for face image with explicit ***,an explicit model(EmFace)for human face representation is pro-posed in the form of a finite sum of mathematical terms,where each term is an analytic function ***,to estimate the unknown parameters of EmFace,a novel neural network,EmNet,is designed with an encoder-decoder structure and trained from massive face images,where the encoder is defined by a deep convolutional neural network and the decoder is an explicit mathematical expression of *** authors demonstrate that our EmFace represents face image more accurate than the comparison method,with an average mean square error of 0.000888,0.000936,0.000953 on LFW,IARPA Janus Benchmark-B,and IJB-C *** results show that,EmFace has a higher representation performance on faces with various expressions,postures,and other ***,EmFace achieves reasonable performance on several face image processing tasks,including face image restoration,denoising,and transformation.