楊佳玲臺灣大學：資訊工程學研究所林恩楷Lin, En-KaiEn-KaiLin2007-11-262018-07-052007-11-262018-07-052007http://ntur.lib.ntu.edu.tw//handle/246246/53704Face detection is the process of locating the position where faces are present in an image.Currently, software-based face detection is hard to support real-time video streams in an embedded processor. By hardware and software co-analysis, we design a hardware imple-mentation of face detection which satisfies embedded constraints. The experimental results of our hardware design show that the video streams provided by RGB camera can be exe-cuted in real-time and the cost of hardware resource is also relatively low. We also analyze our detection rate and false positive number under different threshold settings and lighting conditions.Abstract i 1 Introduction 1 2 Related Work 5 3 Face Detection Algorithm 7 3.1 Skin-Color Filter . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 3.2 Edge Detection . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 3.3 Feature Detection . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 4 Hardware Implementation of Face Detection 14 4.1 Hardware Design Platform . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 4.1.1 Virtex-4 ML402 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 4.1.2 Video I/O Daughter Card . . . . . . . . . . . . . . . . . . . . . . . . 15 4.1.3 LVDS RGB Camera . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 4.1.4 Hardware Platform Diagram . . . . . . . . . . . . . . . . . . . . . . . 16 4.2 Hardware and Software Analysis . . . . . . . . . . . . . . . . . . . . . . . . . 17 4.3 Hardware Implementation of Skin-Color Filter . . . . . . . . . . . . . . . . . 18 4.4 Hardware Implementation of Edge Detection . . . . . . . . . . . . . . . . . . 18 4.5 Hardware Implementation of Feature Detection . . . . . . . . . . . . . . . . 19 4.6 Xilinx Design Flow . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 4.7 Pipelined Flow of Hardware . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 5 Experimental Results 23 6 Conclusion 27774695 bytesapplication/pdfen-US人臉偵測硬體face detectionhardwarethesishttp://ntur.lib.ntu.edu.tw/bitstream/246246/53704/1/ntu-96-R93922107-1.pdf