En savoir plus
This monograph describes the latest advances in discriminative learning methods for biometric recognition. Specifically, it focuses on three representative categories of methods: sparse representation-based classification, metric learning, and discriminative feature representation, together with their applications in palmprint authentication, face recognition and multi-biometrics. The ideas, algorithms, experimental evaluation and underlying rationales are also provided for a better understanding of these methods. Lastly, it discusses several promising research directions in the field of discriminative biometric recognition.
Table des matières
1. Discriminative Learning in Biometrics.- 2. Metric Learning with Biometric Applications.- 3. Sparse Representation-based Classification for Biometric Recognition.- 4. Discriminative Features for Palmprint Authentication.- 5. Orientation Features and Distance Measure of Palmprint Authentication.- 6. Multifeature Palmprint Authentication.- 7. Discriminative Learning via Encouraging Virtual Face Images.- 8. Sparse Representation-based Methods for Face Recognition.- 9. Fusion Methodologies of Multiple Traits.- 10. Discussions and Future Work.
A propos de l'auteur
David Zhang is currently a professor at the Department of Computing, the Hong Kong Polytechnic University where he is the Founding Director of Biometrics Research Centre (UGC/CRC) supported by the Hong Kong SAR Government. He is the book editor of Springer’s International Series on Biometrics (KISB); organizer of the first International Conference on Biometrics Authentication (ICBA); associate editor of more than ten international journals including IEEE Transactions; technical committee chair of the IEEE SMC and the author of more than 10 books and 350 international journal papers. He was listed as a Highly Cited Researcher in Engineering by Thomas Reuters in 2014 and 2015. Professor Zhang is a Croucher senior research fellow, distinguished speaker of the IEEE Computer Society, and a fellow of both the IEEE and IAPR.
Yong Xu currently is a professor at the School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), China. His interests include pattern recognition, biometrics, machine learning, video analysis and bioinformatics. Dr. Xu has designed a number of algorithms for the above fields and has provided effective solutions for real-world pattern and computer vision problems. He has published more than 100 international journal papers, including more than 10 ISI highly cited papers. His prestigious research group has received several awards. Dr. Xu is an associate editor of the International Journal of Image and Graphics, and a senior member of the IEEE. He has published two monographs in English, including Computer Models for Facial Beauty Analysis by Springer, and Advanced Pattern Recognition Technologies with Applications to Biometrics by Medical Information Science Reference.
Wangmeng Zuo currently is a professor at the School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China. His research interests include discriminative learning, deep learning, image modeling and low-level vision, and biometrics. Dr. Zuo has published more than 50 papers in leading academic journals and at conferences. Dr. Zuo is an associate editor of the IET Biometrics, guest editor of Neurocomputing, Pattern Recognition, and IEEE Transactions on Circuits and Systems for Video Technology. He has co-authored a book on medical biometrics and several book chapters on biometrics.
Résumé
This monograph describes the latest advances in discriminative learning methods for biometric recognition. Specifically, it focuses on three representative categories of methods: sparse representation-based classification, metric learning, and discriminative feature representation, together with their applications in palmprint authentication, face recognition and multi-biometrics. The ideas, algorithms, experimental evaluation and underlying rationales are also provided for a better understanding of these methods. Lastly, it discusses several promising research directions in the field of discriminative biometric recognition.
