What can the structure of the palmprint tell us

• Main Author: Leong, Wei Siong.
• Other Authors: Li Fang
• Format: Final Year Project
• Language: English
• Published: 2013
• Subjects: DRNTU::Engineering
• Online Access: http://hdl.handle.net/10356/52493
• Institution: Nanyang Technological University

We know that common authentication technologies like having password, keys or cards, the system only needs to acquire the correct information during the authenticating process and not the authorized person of the password, keys or cards. As a result an unauthorized person can bypass the security system if the person possesses the correct information. This problem shows a demand for higher reliable security system. To overcome that problem, biometrics system is an automated recognition of individual based on their biological or measurable behavior characteristics. Human characteristic such as fingerprint, iris, voice, hand geometry, palmprint, hand vein and many are used to verify an identity as these are unique human characteristic. With biometrics system authorized person will be correctly identified and unauthorized person trying to bypass the security system will not be allowed.This project studies hand vein patterns as a biometric feature and it will be used as input for two algorithms which are combined histogram and fast-match to do identification. During the extraction process of hand vein, there will always be difficulty in matching because of distorted or broken lines. Aligning of hand vein is a challenging job in image preprocessing as most matching systems rely on perfect alignment. To overcome alignment problem which is related to rotation, scaling and translation (RST), special image acquisition devices is used to restrict the movement and positioning of the hand during the acquisition process in order to improve the image quality. However, to improve mobility as not to restrict the movement and positioning of the hand a pair-wise angle relationships algorithm is used among lines are extracted to present the local structure of line pattern. Pair-wise angle relationships are simple, invariant to translation and rotation, robust to end-point erosion and segment error, and sufficient for discrimination.