本篇論文提出手指靜脈之使用者辨識系統，開發在單晶片微處理器系統上。以CCD攝影機取得光穿透手指靜脈影像，經由C8051微處理器硬體實現影像切割處理與識別。本篇論文可分為兩個主要部分。第一部分為手指靜脈影像處理演算法的建構。第二部分為單晶片C8051手指靜脈血管影像處理的硬體實作方法，整個影像處理的步驟，包括二值化、中值濾波器、指靜脈影像使用者辨識等處理，這些方法都是使用Keil C程式語言所撰寫。我們初步的實驗結果可得知，此系統具可靠性與高準確率，且為低成本和高安全性的使用者辨識系統，未來將可應用於日常生活之中。This thesis aims at developing a microprocessor-based system to achieve a finger-vein user identification system. Light-transmitted finger images were acquired using a CCD camera, and the finger-vein images were subsequently segmented and recognized using hardware implemented on a C8051 microprocessor. The contributions of this thesis can be divided into two parts. The first part is the formation of image processing algorithm for finger-vein image segmentation. The second part is the hardware implementation of the proposed finger-vein image processing on a C8051 microprocessor. The whole processing steps, including binarization, median filter, and user recognition using images of finger vein, were performed on hardware written in Keil C computer language. Our preliminary results demonstrated the proposed system provides reliable and high-accuracy results, which can be used as a low-cost and high-security user identification system for daily-life applications in the future.
