[1]DU Jixiang,ZHAI Chuanmin,YE Yongqing.An agespan face recognition method based on an NMF algorithm with sparseness constraints[J].CAAI Transactions on Intelligent Systems,2012,7(3):271-277.
Copy

An agespan face recognition method based on  an NMF algorithm with sparseness constraints

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 7 Number of periods: 2012 3 Page number: 271-277 Column: 学术论文—机器感知与模式识别 Public date: 2012-06-25
Title:
An agespan face recognition method based on  an NMF algorithm with sparseness constraints
Author(s):
DU Jixiang;  ZHAI Chuanmin;  YE Yongqing
Department of Computer Science and Technology, Huaqiao University, Xiamen 361021, China
Keywords:
face recognition;  agespan face recognition;  nonnegative matrix factorization algorithm;  sparseness constraints;  facial aging simulation;  virtual samples
CLC:
TP391
DOI:
-
Abstract:
For face recognition technology, apart from lighting, gesture, and expression factors, variations in shape and texture of human faces due to aging factors also significantly affect the performance of face recognition systems. Using a sparseconstrained nonnegative matrix factorization (NMF) algorithm, a facial aging simulation method based on an improved prototype was first proposed and then applied to agespan face recognition to add virtual samples and heighten the recognition rate. Experimental results show that the age span indeed has a great effect on face recognition; the NMF algorithm has stronger feature extraction ability when the coefficient matrix is sparsely constrained. Furthermore, the recognition ratio is apparently improved after adding additional virtual samples by aging simulation of face texture features. 
References:
［1］PHILLIPS P J, SCRUGGS W T, O’TOOLE A J, et al. FRVT 2006 and ICE 2006 largescale results: Technical Report NISTIR 7408［R］. Gaithersburg, USA: National Institute of Standards and Technology, 2007.
［2］RAMANATHAN N, CHELLAPPA R. Face verification across age progression［J］. IEEE Transactions on Image Processing, 2006, 15(11): 33493361.
［3］TODD J T, MARK L S, SHAW R E, et al. The perception of human growth［J］. Scientific American, 1980, 242(2): 132144.
［4］BURT M, PERRETT D. Perception of age in adult Caucasian male faces computer graphic manipulation of shape and colour information［J］. Proceedings of the Royal Society B: Biological Sciences, 1995, 259(1355): 137143.
［5］TIDDEMAN B, BURT M, PERRETT D. Prototyping and transforming facial texture for perception research［J］. IEEE Computer Graphics and Applications, 2001, 21(5): 4250.
［6］许志维，张轩庭．基于非负矩阵分解演算法预测未来人脸影像［C］//2005年消费者电子信号处理研讨会. ［S.l.］, China, 2005: 18.
?XU Zhiwei, ZHANG Xuanting. Prediction of future facial image based on NMF algorithm［C］//Proceedings of the 2005 Workshop on Consumer Electronics and Signal Processing (WCEsp2005). ［S.l.］, China: 2005: 18.
［7］王章野，曹玫璇，李理，等．基于个性化原型的人脸衰老图像合成［J］．电子学报, 2009, 37(4A): 118124.
WANG Zhangye, CAO Meixuan, LI li, et al. Individual prototyping based facial aging image synthesis［J］. Chinese Journal of Electronics, 2009, 37(4A): 118124.
［8］HOYER P O. Nonnegative matrix factorization with sparseness constraints［J］. Journal of Machine Learning Research, 2004, 5: 14571469.
［9］JENKINS R, BURTON A M, WHITE D. Face recognition from unconstrained images: progress with prototypes［C］//Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition. Washington, DC, USA: IEEE Computer Society, 2006: 2530.
［10］戴欢，吴小俊．基于图像欧式距离的人脸描述和识别方法［J］．江南大学学报：自然科学版, 2009, 8(1): 2023.
DAI Huan, WU Xiaojun. Face representation and recognition based on image Euclidean distance［J］. Journal of Jiangnan University: National Science Edition, 2009, 8(1): 2023.
［11］Face and Gesture Recognition Research Network. FGNet aging database［EB/OL］. ［20111207］.
Similar References:

Memo

-

Last Update: 2012-09-05

Copyright © CAAI Transactions on Intelligent Systems