掌形辨識實作

Implementation of Hand-Shape Recognition

程宏琪(Hung-Chi Cheng)

指導教授 ： 陳文雄

國立暨南國際大學/科技學院/電機工程學系/碩士(2010年)

摘要

科技日新月異，對生活品質及安全問題日漸重視，舊有的辨識技術雖然仍廣泛受到使用，但在現今社會已經略顯不足，而使得以生物辨識為基礎的身份辨識技術逐漸為大眾所接受。 生物辨識包括許多不同的技術，本論文將探討以掌形特徵為基礎的辨識技術，並且實作出一套辨識率佳的掌形辨識系統。系統架構主要包含四個模組：影像擷取模組、影像前處理模組、特徵萃取和分類辨識模組，透過友善的圖形介面將各模組之間進行連結，讓使用者能輕易的操作此系統。系統模組中，首先經由網路攝影機把即時輸入影像定位並擷取出掌形影像，再經前處理可將截取出的掌形影像進行手指定位並將之擷取出，接著以(2D)2-PCA對手指影像進行降維後編成身份特徵碼，最後以此身份特徵碼進行註冊或辨識動作。 系統資料庫實是由本實驗室自行建立的，30位自願的同學進行手掌拍攝，並將身份特徵碼註冊入資料庫中，再個別進行即時的辨識測詴。經測詴統計辨識率達到81.33%。

關鍵字

生物辨識 ； 掌形辨識 ； 雙向的二維主成份分析

並列摘要

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%.

並列關鍵字

Biometrics ； Hand-shape Recognition ； (2D)2-PCA

參考文獻

[1] R. P. Miller, “Finger dimension comparison identification system,” US Patent, no. 3576538, 1971.

[2] R. H. Emst, “Hand id system,” US Patent, no. 3576537, 1971.

[3] H. Jacoby, A. J. Giordano, and W. H. Fioretti, “Personnel identification apparatus,” US Patent, no. 3648240, 1986.

[4] H. Yoshikawa and S. Ikebata, “A microcomputer-based personal identification system,” Proc. of International Conf. on Industrial Electronics, Control and Instrumentation, vol. 1, pp. 105-109, 1984.

[5] J. Svigals, “Low cost personal identification verification device based on finger dimensions,” IBM Technical Disclosure Bulletin, vol. 25, no. 4, 1982.