Implementation of Hand-Shape Recognition

• Main Authors: Hung-Chi Cheng, 程宏琪
• Other Authors: Wen-Shiung Chen
• Format: Others
• Language: zh-TW
• Published: 2010
• Online Access: http://ndltd.ncl.edu.tw/handle/73785225128477333867

碩士 === 國立暨南國際大學 === 電機工程學系 === 98 === In recent year, with an increasing emphasis on security, although the traditional identification techniques are still widely used, not enough for today’s need, so based on Biometrics identity recognition technologies is increasingly accepted by the public. Biometrics including many different technologies, in this thesis, we examine hand-shape recognition system based on human hand-shape feature, and implement a good performance recognition system based on human hand-shape feature. This system includes four modules: image acquisition module, image pre-processing module, feature extraction module, and recognition module. We use friendly graphical user interface to link every modules, so users can easily operate this system. In all modules, first, locate the hand-shape form real-time images by use webcam, and obtain the fingers from the hand image via image pre-processing module. Then we employ the (2D)2-PCA to reduce the fingers data and code to identity feature code. Eventually, the identity feature code will be used to register or recognition. The system database is established by our own laboratory, which totally contains 30 volunteers, we capture hand image from each one of volunteer and registered it. Then, the 30 volunteers tested the performance of the system. The experimented results show the recognition rate is 81.33%.