研究生: |
呂元昊 Yuan-hao Lu |
---|---|
論文名稱: |
以SOPC為基礎之人臉辨識系統 SOPC Based Face Recognition System |
指導教授: |
許孟超
Mon-chau Shie |
口試委員: |
梁文耀
none 陳伯奇 none 阮聖彰 none |
學位類別: |
碩士 Master |
系所名稱: |
電資學院 - 電子工程系 Department of Electronic and Computer Engineering |
論文出版年: | 2005 |
畢業學年度: | 93 |
語文別: | 中文 |
論文頁數: | 40 |
中文關鍵詞: | 人臉辨識 |
外文關鍵詞: | SOPC, face recognition |
相關次數: | 點閱:205 下載:1 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
人臉辨識系統,主要是以生物特徵來辨識個人身分。本論文以SOPC為基礎,使用二維離散小波轉換(2-D Discrete Wavelet Transform),取出人臉影像的低頻係數,做為人臉影像特徵參數,以降低影像維度,增進人臉特徵與資料庫比對的速率。
Altera的SOPC (System On Programmable Chip)為一個FPGA,內含有一個軟核32-bit RISC處理器,可以輕易的加入自行定義的硬體模組與處理器結合。SOPC具有完善的硬體模組函式庫,良好撰寫C程式語言的使用者介面,具有硬體執行速度快的特性與軟體容易修改的特點,在開發上比ASIC具彈性,在消耗功率上比個人電腦低。二維離散小波轉換採用升級式機制(Lifting Base)濾波器做為人臉辨識系統的核心。升級式機制具有運算量小、容易以硬體實現的優點。用硬體描述語言撰寫升級式機制濾波器,與本系統結合,來縮短其運算時間,以達成即時辨識之目標。並以高度整合性的SOPC為實做平台,建立本系統。
本論文在SOPC FPGA平台上實做小波轉換之人臉辨識系統,最後針對一套61人的人臉資料庫中做測試,經實驗證實,本論文所開發的系統,可以得到極佳的辯識率。
The face recognition system is mainly developed for identifying personal identities based on biometrics information. Based on SOPC, our approach reduces the dimension of images by employs 2-D DWT to extract low frequency coefficients of face images as the features of face images. And therefore accelerates the speed of matching with database transactions.
Altera's FPGA based SOPC used in the thesis includes a soft-core 32-bit RISC micro-processor, user-defined hardware modules can be easily combined with the micro-processor. SOPC has advantages in several ways: 1) complete hardware module library, 2) friendly user interface for writing C code, 3) fast hardware execution speed, 4) software can be easily developed, 5) more flexible than ASIC for development and 6) lower power consumption than personal computers. The 2-D DWT employs a Lifting Base filter, which the computational complexity is low, for face recognition system. Achieving the goal of real-time recognition, we implement the lifting base filter by HDL and combine with our system for reduce the computational latency. The system is constructed on the SOPC platform, which of highly integrated system.
In the experiments, we implement 2-D DWT approach face recognition scheme into SOPC FPGA system, we use it to conduct a series of evaluation on a face database consisting of 61 persons. The result shows that recognition rate is good.
[1] Po-Cheng Wu and Liang-Gee Chen, “An Efficient Architecture for Two-Dimensional Discrete Wavelet Transform,” IEEE Trans. Circuits and Systems for Video Technology, vol. 11, no. 4, pp.536 – 545, April 2001.
[2] Chu Yu, Chien-An Hsieh and Sao-Jie Chen, “Design and Implementation of a Highly Efficient VLSI Architecture for Discrete Wavelet Transform,” Proc. Of IEEE Custom Integrated Circuits Conference, pp.237 – 240, 1997.
[3] 吳忠政,二維三階上提式離散小波轉換架構,南台科技大學電子工程學系碩士論文,民國91年。
[4] 吳佳珍,以鑑別性小波參數為主之人臉辨識系統,國立成功大學資訊工程學系碩士論文,民國90年。
[5] 黃泰祥,具備人臉追蹤與辨識功能的一個智慧型數位監視系統,中原大學電子工程學系碩士論文,民國93年。
[6] 江文盛,低硬體成本有效的離散小波轉換VLSI架構,國立台北科技大學電腦通訊與控制研究所碩士論文,民國91年。
[7] 胡毓宗, JPEG2000 靜態影像壓縮編碼器之系統設計與晶片實現,國立成功大學電機工程學系碩士論文,民國91年。
[8] Tinku Acharya, Ping-Sing Tsai, JPEG2000 Standard for Image Compression: Concepts, Algorithms and VLSI Architectures, John Wiley & Sons, 2004.
[9] Steve Lawrence, C. Lee Giles , Ah Chung Tsoi , Andrew D. Back , “Face recognition: a convolutional neural-network approach,” IEEE Trans. Neural Networks , vol.8 , no.1 , pp.98-113 , Jan. 1997 .
[10] S. G. Mallat, “Multifrequency channel decompositions of images and wavelet models,” IEEE Tran. Acoustics, Speech and Signal Processing, vol. 37, no. 12, pp. 2091-2110, Dec. 1989.
[11] M. Vishwanath, “The recursive pyramid algorithm for the discrete wavelet transform,” IEEE Tran. Signal Processing, vol. 42, no. 3, pp. 673-676, Mar. 1994.
[12] W. Sweldens, “The lifting scheme: A custom-design construction of biorthogonal wavelet,” Applied and Computational Harmonic Analysis, vol. 3, pp. 186-200, 1996.
[13] D. Le Gall, A. Tabatabai, “Sub-band coding of digital images using symmetric short kernel filters and arithmetic coding techniques,” Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol.2, pp. 761 – 764, Apr. 1988.
[14] S.Z. Li , J. Lu, ”Face Recognition Using the Nearest Feature Line Method,” IEEE Trans. Neural Networks , vol.10 , no.2 , pp. 439-443, March 1999.
[15] M. Nagao, M. Yamamoto, K. Suzuki, A. Ohuchi ,”MTS Approach to Facial Image Recognition,” Proc. IEEE Conf. On Systems, Man, and Cybernetics. Vol.4 , pp. 937-942 , 1999.
[16] 戴顯權、陳政一,JPEG2000,紳藍出版社,2002