Advanced Study on Biometrics

Nowadays, biometrics has become the most popular recognition system for protecting privacy and important information. However, the recognition performance is sensitive to the changes of shooting angle, lighting conditions, as well as the environments. To deal with these issues, a three-year research project is conducted as follows. 1) High efficiency noise reduced regional contrast enhancement method 2) Texture-property-based finger-vein recognition system 3) A new ear recognition system with geometric correction and coordinate correspondence In the progress of the first-year project, the issues of the regional contrast enhancement and noise reduction will be addressed for practical applications. In addition, a new algorithm and its concept are also proposed for yield less computational complexity. In the system of the second-year project, the outcome of the first year will be applied for image normalization. In fact, the functionality of project in the first year will offer a great advantage for the finger-vein’s textures extraction, and reduce a huge amount of noises for better image quality. Moreover, the image normalization provides a stable feature for higher recognition accuracy. In the third-year project, it mainly offers a capability of identity recognition from any view-angle. In addition, this project considers a state-of-the-art accelerated-KAZE (A-KAZE) to extract the key points of the ears for feature stability. These points will then be transformed for rotation correction. Finally, the ROC will be used as the major measure for performance evaluation.

Project ID:PB10408-5727
External Project ID:MOST104-2221-E182-052-MY2