Department of Computing
The Hong Kong Polytechnic University
Biometrics is concerned with identifying a person by his/her physiological characteristics, such as iris, retina, fingerprint and face. Behavior characteristics, such as voice, signature and gesture are also aspects of biometric identification. Although research on fingerprint identification and speech recognition has drawn considerable attention over the last 25 years and although, more recently, face recognition and iris-based verification have been studied extensively, there are still some limitations to existing applications. Some people have their fingerprints worn or deformed over time due to handwork and some are born without well formed fingerprints. Iris and retina recognition can provide a high accuracy but they suffer from the high cost of the input devices, and are more intrusive to the users. Face and voice based identification systems are less accurate and easy to be mimicked. Research efforts on improving the current personal identification approaches are still continuing and new algorithms are emerging.
Palmprint authentication was explored for the first time by the author and his working team more than five years ago. Now, it is regarded as a new attempt and a necessary complement to the existing biometric measures. Unlike hand geometry that measures a hand's size and fingers' length, palmprint is concerned with the inner surface of a hand and looks at line patterns and surface shape. A palm is covered with the same kind of skin as the fingertips and it is larger than a fingertip in size. Hence, it is quite natural to think of using palmprint to recognize a person.
The research on palmprint initiated from palm reading, which had its roots both in China and in India. This work has propagated into the western countries afterwards. A lot of palmprint observational records and statistics have been accumulated through a few thousands of years. However, only a few articles have been published. These are exclusively devoted to palmprint identification and verification, despite the importance of palmprint features.
In this tutorial I will systematically introduce the relative technologies on palmprint authentication and explore how to design the corresponding systems with an in-depth discussion. But, this is not meant to suggest a low-relevance of the palmprint authentication. Rather, in this tutorial I will address highly relevant issues and fundamental concerns of both researchers and practitioners of automated palmprint authentication in security and detection systems. The material in the tutorial is the outgrowth of the author's and his team's research work, including the former work and the recent academic achievements. Although, for the sake of completeness, related work of other authors will also be addressed.
This tutorial is organized into three parts. Part I describes off-line palmprint authentication technologies. Part II introduces on-line palmprint authentication technologies. Part III mainly contains discussions on palmprint authentication system. As a result, a practical palmprint identification system prototype is presented. Finally, future directions in biometrics are discussed.
Prof. David Zhang graduated in computer science from Peking University in 1974 and received his MSc and PhD degrees in computer science and engineering from the Harbin Institute of Technology (HIT) in 1983 and 1985, respectively. From 1986 to 1988, he was a postdoctoral fellow at Tsinghua University, and he became an associate professor at Academia Sinica, Beijing, China. He received his second PhD in electrical and computer engineering at the University of Waterloo, Ontario, Canada, in 1994. Currently, he is a Professor in the Hong Kong Polytechnic University. He is Founder and Director of Biometrics Technology Centers supported by UGC/CRC, the Government of the Hong Kong SAR. He is Founder and Editor-in-Chief, of the International Journal of Image and Graphics (IJIG), and Associate Editor of over ten international journals, such as IEEE Trans. on SMC and Pattern Recognition. He is also a Guest Editor of IEEE Trans. on SMC, special issue on Biometrics Systems (2003) and Pattern Recognition, special issue on Biometrics Authentication (2002), and a Book Series Editor of International Kluwer Series on Biometrics. He is Program Chair of the International Conference on Biometric Authentication, 8-10 January 2004, Hong Kong. As a principal investigator, he has finished many biometrics projects since 1980. He is the first researcher to work on palmprint authentication in the world. So far, he and his working team have set up a largest palmprint image database (>100,000 samples), finished the first palmprint identification prototype awarded as the silver medal in The Seoul International Invention Fair (SIIF 4-8 December 2002), and obtained four patents related to palmprint authentication. Until now, he has published over 200 papers and seven books, including Automated Biometrics: Technologies and Systems (2000), Data Management and Internet Computing for Image/Pattern Analysis (2001), Biometrics Resolutions for Authentication in an e-World (2002) and Palmprint Authentication (2003).