计算机应用 ›› 2017, Vol. 37 ›› Issue (3): 896-900.DOI: 10.11772/j.issn.1001-9081.2017.03.896

• 应用前沿、交叉与综合 • 上一篇    下一篇

基于多任务学习的多姿态人脸重建与识别

欧阳宁1,2, 马玉涛2, 林乐平1,2   

  1. 1. 认知无线电与信息处理省部共建教育部重点实验室(桂林电子科技大学), 广西 桂林 541004;
    2. 桂林电子科技大学 信息与通信学院, 广西 桂林 541004
  • 收稿日期:2016-08-01 修回日期:2016-09-07 出版日期:2017-03-10 发布日期:2017-03-22
  • 通讯作者: 林乐平
  • 作者简介:欧阳宁(1972-),男,湖南宁远人,教授,硕士,主要研究方向:数字图像处理、智能信息处理;马玉涛(1991-),女,内蒙古乌兰察布人,硕士研究生,主要研究方向:人脸识别、深度学习;林乐平(1980-),女,广西桂平人,博士,主要研究方向:模式识别、智能信息处理、图像信号处理。
  • 基金资助:
    国家自然科学基金资助项目(61362021,61661017);广西自然科学基金资助项目(2013GXNSFDA019030,2014GXNSFDA118035);广西科技创新能力与条件建设计划项目(桂科能1598025-21);桂林科技开发项目(20150103-6)。

Multi-pose face reconstruction and recognition based on multi-task learning

OUYANG Ning1,2, MA Yutao2, LIN Leping1,2   

  1. 1. Key Laboratory of Cognitive Radio and Information Processing, Ministry of Education(Guilin University of Electronic Technology), Guilin Guangxi 541004, China;
    2. School of Information and Communication, Guilin University of Electronic Technology, Guilin Guangxi 541004, China
  • Received:2016-08-01 Revised:2016-09-07 Online:2017-03-10 Published:2017-03-22
  • Supported by:
    This work is partially supported by the Natural Science Foundation of China (61362021, 61661017), the Natural Science Foundation of Guangxi (2013GXNSFDA019030, 2014GXNSFDA118035), the Scientific and Technological Innovation Ability and Condition Construction Plan of Guangxi (1598025-21), the Scientific and Technological Development Project of Guilin (20150103-6).

摘要: 针对当前人脸识别中姿态变化会影响识别性能,以及姿态恢复过程中脸部局部细节信息容易丢失的问题,提出一种基于多任务学习的多姿态人脸重建与识别方法——多任务学习堆叠自编码器(MtLSAE)。该方法通过运用多任务学习机制,联合考虑人脸姿态恢复和脸部局部细节信息保留这两个相关的任务,在步进逐层恢复正面人脸姿态的同时,引入非负约束稀疏自编码器,使得非负约束稀疏自编码器能够学习到人脸部的部分特征;其次在姿态恢复和局部信息保留两个任务之间通过共享参数的方式来学习整个网络框架;最后将重建出来的正脸图像通过Fisherface进行降维并提取具有判别信息的特征,并用最近邻分类器来识别。实验结果表明,MtLSAE方法获得了较好的姿态重建质量,保留的局部纹理信息清晰,而且与局部Gabor二值模式(LGBP)、基于视角的主动外观模型(VAAM)以及堆叠步进自编码器(SPAE)等经典方法相比,识别率性能得以提升。

关键词: 多任务学习, 姿态恢复, 局部细节信息, 自编码器, 共享参数

Abstract: To circumvent the influence of pose variance on face recognition performance and considerable probability of losing the facial local detail information in the process of pose recovery, a multi-pose face reconstruction and recognition method based on multi-task learning was proposed, namely Multi-task Learning Stacked Auto-encoder (MtLSAE). Considering the correlation between pose recovery and retaining local detail information, multi-task learning mechanism was used and sparse auto-encoder with non-negativity constraints was introduced by MtLSAE to learn part features of the face when recovering frontal images using step-wise approach. And then the whole net framework was learned by sharing parameters between above two related tasks. Finally, Fisherface was used for dimensionality reduction and extracting discriminative features of reconstructed positive face image, and the nearest neighbor classifier was used for recognition. The experimental results demonstrate that MtLSAE achieves good pose reconstruction quality and makes facial local texture information clear; on the other hand, it also achieves higher recognition rate than some classical methods such as Local Gabor Binary Pattern(LGBP), View-Based Active Appearance (VAAM) and Stacked Progressive Auto-encoder (SPAE).

Key words: multi-task learning, pose recovery, local detail information, auto-encoder, sharing parameter

中图分类号: