IR and visible light face recognition

被引:124
作者
Chen, X [1 ]
Flynn, PJ [1 ]
Bowyer, KW [1 ]
机构
[1] Univ Notre Dame, Dept Comp Sci & Engn, Notre Dame, IN 46556 USA
基金
美国国家科学基金会;
关键词
multi-modal; biometrics; face recognition; infrared imaging; principal components analysis;
D O I
10.1016/j.cviu.2005.03.001
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper presents the results or several large-scale studies or race recognition employing visible-light and infrared (IR) imagery in the context of principal component analysis. We find that in a scenario involving time lapse between gallery and probe. and relatively controlled lighting, (1) PCA-based recognition using visible-light images Outperforms PCA-based recognition using infrared images, (2) the combination of PCA-based recognition using Visible-light and infrared imagery substantially outperforms either one individually. I it it same-session scenario (i.e., near-simultaneous acquisition of gallery and probe images) neither modality is significantly better than the other. These experimental results reinrorce prior research that employed a smaller data set, presenting it convincing argument that. even across it broad experimental spectrum, the behaviors enumerated above are valid and consistent, (c) 2005 Elsevier Inc. All rights reserved.
引用
收藏
页码:332 / 358
页数:27
相关论文
共 27 条
[21]  
Socolinsky DA, 2002, INT C PATT RECOG, P217, DOI 10.1109/ICPR.2002.1047436
[22]  
SOCOLINSKY DA, 2004, 17 INT C ICPR 04 AUG, V4, P187
[23]  
SOCOLINSKYD, 2001, COMPUT VISION PATTER, V1, P527
[24]   Statistical hypothesis pruning for identifying faces from infrared images [J].
Srivastava, A ;
Liu, XW .
IMAGE AND VISION COMPUTING, 2003, 21 (07) :651-661
[25]  
TURK M, 1991, COMPUT VISION PATTER
[26]   Comparison of visible and infra-red imagery for face recognition [J].
Wilder, J ;
Phillips, PJ ;
Jiang, CH ;
Wiener, S .
PROCEEDINGS OF THE SECOND INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION, 1996, :182-187
[27]  
YAMBOR WS, 2000, EMPIRICAL EVALUATION