Discriminant Correlation Analysis: Real-Time Feature Level Fusion for Multimodal Biometric Recognition

被引:259
作者
Haghighat, Mohammad [1 ]
Abdel-Mottaleb, Mohamed [1 ]
Alhalabi, Wadee [2 ,3 ]
机构
[1] Univ Miami, Dept Elect & Comp Engn, Coll Engn, Coral Gables, FL 33146 USA
[2] Effat Univ, Dept Comp Sci, Jeddah 21478, Saudi Arabia
[3] King Abdulaziz Univ, Dept Comp Sci, Jeddah 21589, Saudi Arabia
关键词
Multimodal biometrics; feature level fusion; class structure; discriminant correlation analysis; CANONICAL CORRELATION-ANALYSIS; FACE RECOGNITION; NORMALIZATION; FINGERPRINT; EIGENFACES;
D O I
10.1109/TIFS.2016.2569061
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Information fusion is a key step in multimodal biometric systems. The fusion of information can occur at different levels of a recognition system, i.e., at the feature level, matching-score level, or decision level. However, feature level fusion is believed to be more effective owing to the fact that a feature set contains richer information about the input biometric data than the matching score or the output decision of a classifier. The goal of feature fusion for recognition is to combine relevant information from two or more feature vectors into a single one with more discriminative power than any of the input feature vectors. In pattern recognition problems, we are also interested in separating the classes. In this paper, we present discriminant correlation analysis (DCA), a feature level fusion technique that incorporates the class associations into the correlation analysis of the feature sets. DCA performs an effective feature fusion by maximizing the pairwise correlations across the two feature sets and, at the same time, eliminating the between-class correlations and restricting the correlations to be within the classes. Our proposed method can be used in pattern recognition applications for fusing the features extracted from multiple modalities or combining different feature vectors extracted from a single modality. It is noteworthy that DCA is the first technique that considers class structure in feature fusion. Moreover, it has a very low computational complexity and it can be employed in real-time applications. Multiple sets of experiments performed on various biometric databases and using different feature extraction techniques, show the effectiveness of our proposed method, which outperforms other state-of-the-art approaches.
引用
收藏
页码:1984 / 1996
页数:13
相关论文
共 60 条
[1]   A Survey on Ear Biometrics [J].
Abaza, Ayman ;
Ross, Arun ;
Hebert, Christina ;
Harrison, Mary Ann F. ;
Nixon, Mark S. .
ACM COMPUTING SURVEYS, 2013, 45 (02)
[2]  
[Anonymous], 1998, 24 CVC AUT U BARC
[3]  
[Anonymous], 2008, VLFeat: An open and portable library of computer vision algorithms
[4]   Multimodal Task-Driven Dictionary Learning for Image Classification [J].
Bahrampour, Soheil ;
Nasrabadi, Nasser M. ;
Ray, Asok ;
Jenkins, William Kenneth .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2016, 25 (01) :24-38
[5]   Real time face and mouth recognition using radial basis function neural networks [J].
Balasubramanian, M. ;
Palanivel, S. ;
Ramalingam, V. .
EXPERT SYSTEMS WITH APPLICATIONS, 2009, 36 (03) :6879-6888
[6]   Speeded-Up Robust Features (SURF) [J].
Bay, Herbert ;
Ess, Andreas ;
Tuytelaars, Tinne ;
Van Gool, Luc .
COMPUTER VISION AND IMAGE UNDERSTANDING, 2008, 110 (03) :346-359
[7]   Eigenfaces vs. Fisherfaces: Recognition using class specific linear projection [J].
Belhumeur, PN ;
Hespanha, JP ;
Kriegman, DJ .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1997, 19 (07) :711-720
[8]  
Bishop C.M., 2006, PATTERN RECOGN, V4, P738, DOI DOI 10.1117/1.2819119
[9]  
Chikkerur S, 2004, LECT NOTES COMPUT SC, V3072, P344
[10]   Canonical Correlation Analysis for Data Fusion and Group Inferences [J].
Correa, Nicolle M. ;
Adali, Tulay ;
Li, Yi-Ou ;
Calhoun, Vince D. .
IEEE SIGNAL PROCESSING MAGAZINE, 2010, 27 (04) :39-50