Palm-Print and Hand-Shape Biometric Recognition System Based on Wavelet Transform and Statistical Moments

• Main Authors: Chiang, Yao-Shan, 江樂山
• Other Authors: Chen, Wen-Shiung
• Format: Others
• Language: zh-TW
• Published: 2005
• Online Access: http://ndltd.ncl.edu.tw/handle/65358393795776210022

碩士 === 國立暨南國際大學 === 電機工程學系 === 93 === With an increasing emphasis on security, personal authentication based on biometrics has been receiving extensive attention over the past decade. Among many different biometric technologies, this thesis examines palm-print and hand-shape technique for personal identification and develops a good performance recognition system based on human hand features. It is implemented and tested on VIP-CC Lab. hand image database. The proposed system includes four modules: image acquisition, image pre-processing, feature extraction, and recognition modules. First, the system captures a hand image using digital camera, then uses some image processing algorithms to localize the region of the interest of palm-print and hand-geometry from the hand image via image pre-processing module. The feature extraction module adopts the gradient direction （i.e., angle） of the two different wavelet transforms in the palm-print phase, and adopts the statistical moments in the hand-shape to extract the discriminating texture features. The system encodes the feature to generate its palm-print codes by binary gray coding, and uses invariant moment vector in hand-geometry phase. Finally, the system applies these feature codes and vector for matching in recognition module. Experimental results show that the system has an encouraging performance on the VIP-CC Lab. database（including 210 images from 30 classes）. The proposed system adopts two different wavelet transform and statistical moments to extract palm-print and hand-shape features, then uses the gradient direction coding to generate the feature codes. We attain the recognition rates up to 95.00% and 98.33%（according to equal error rate, EER）, respectively. Even under the circumstance of false acceptance rate（FAR） 0%, the system still approaches the recognition rate above 89.17%（acceptance of authentic, AA）. This thesis analyzes the experimented results and verifies the related inferences of the proposed system for providing useful information for further research.