臺灣博碩士論文加值系統

本論文提出一套實現於嵌入式平台之車牌辨識系統。演算法主要是以Ada-Boost將影像中的車牌抓出來。接著將偵測到的車牌去做文字切割，將切割後得到的字元各別去計算其特徵，再將特徵丟給SVM辨識出其結果。最後將SVM得到的結果，再經由一個車牌文法檢查去過濾其不正確的車牌結果。
我們使用的嵌入式平台為德州儀器(Texas Instruments , TI)的DaVinci 6446，此平台是由ARM與DSP構成的。在這個雙核心平台裡ARM負責系統的控制，DSP負責演算法中複雜的數學運算。我們藉著ARM與DSP兩顆核心之間互相的合作，讓處理速度可達到即時的效果。我們的系統處理速度約每張影像41ms左右，其效能大約25 FPS。

In this paper, we present a license plate recognition system in the embedded system platform. Our system employs the Ada-Boosting technique to train the model in order to detect the license plate. After the license plate is detected, this system will segment the license plate into some characters and will extract the features. Subsequently, we use the SVM classifier to classify the feature classes so as to recognize the accurate character’s meaning. Finally, these meaningful characters are checked by the mechanism of syntax analysis in order to differentiate the false results. Our embedded system DaVinci 6446 platform is composed of the ARM and DSP units, which is manufactured by the Texas Instruments. DaVinci 6446 platform is a two-core processor. ARM is responsible for the system control and DSP processes the complex mathematical operation. By the cooperation of the two cores, the performance can achieve real-time processing. Our system obtains an average processing time of 41ms per frames, about 25 fps.

摘 要 i
Abstract ii
誌 謝 iii
目錄 iv
圖目錄 vi
表目錄 viii
第一章 緒論 1
1.1 研究動機 1
1.2 研究方法 2
1.3 文獻探討 3
1.4 論文架構 6
第二章 偵測與辨識的技術 7
2.1 Ada-Boosting簡介 7
2.2 偵測方法 10
2.2.1 特徵 10
2.2.2 車牌樣本 10
2.2.3 串聯運算 12
2.2.4 積分影像(Integral Image) 14
2.2.5 車牌偵測 15
2.2.6 區域整合 16
2.3 文字切割 16
2.4 字元辨識 18
2.4.1 特徵計算 19
2.4.2 SVM (Support Vector Machine) 20
2.5 字串切割 23
第三章 TI DaVinci技術介紹 24
3.1 TI DaVinci 6446硬體架構 26
3.2 TI DaVinci 6446軟體架構 28
3.3 Codec Engine 30
3.3.1 Codec Engine工作原理 30
3.3.2 Codec Engine與Codec Server 的RPC工作原理 39
第四章 TI DaVinci實現與優化 40
4.1 開發環境 40
4.2 XDC(Express DSP Component) 41
4.3 設定Codec Engine 43
4.3.1 本地執行 44
4.3.2 遠端執行 44
4.4 建立Codec Server 45
4.4.1 Codec Server設定 46
4.4.2 XDC建立Codec Server 47
4.5 CMEM 48
4.6 ARM與DSP之間數據的傳遞 51
4.7 DSP程式優化 52
4.8 Q格式 55
4.8.1 Q格式的運算 57
第五章 實驗結果 60
5.1 執行效能 61
5.2 車牌偵測與辨識 63
第六章 結論與未來展望 70
參考文獻 71

[1]T. Naito, “Robust recognition methods for inclined license plates under various illumination condition outdoors,” Proc. of IEEE/IEEJ/JSAI International Conference on Intelligent Transportation Systems, pp. 697–702,1999.
[2]C. Busch, R. Domer, C. Freytag and H. Ziegler, “Feature based recognition of traffic video streams for online route tracing,” Proc. of IEEE Conference on Vehicular Technology, vol. 3, pp.1790-1794, 1998.
[3]R. Zunino and S. Rovetta, “Vector quantization for license-plate location and image coding,” IEEE Transactions on Industrial Electronics, vol. 47, pp.159–167, Feb. 2000.
[4]R. Plamondon and S. N. Srihari, “On-line and off-line handwriting recognition: a comprehensive survey,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 22, no. 1, pp.63-84, Jan., 2000.
[5]M. Shridhar, Miller, G. Houle, and L. Bijnagte, “Recognition of license plate images: issues and perspectives,” Proc. of the Fifth International Conference on Document Analysis and Recognition, p.17–20, 1999.
[6]K. K. Kim, et al., “Learning-based approach for license plate recognition,” Proc. of IEEE Workshop on Neural Networks for Signal Processing, vol. 2, pp.614–623, 2000.
[7]H.A. Hegt, R.J. Haye and N.A. Khan, “A high performance license plate recognition system,” Proc. of IEEE International Conference on Systems, Man, and Cybernetics, pp. 4357–4362, 1999.
[8]Y. Mei and D.Y. Yong, “An approach to Korean license plate recognition based on vertical edge matching,” Proc. of IEEE International Conference on Systems, Man, and Cybernetics, pp.2975–2980, 2000.
[9]D. S. Kim and S.I. Chien, “Automatic car license plate extraction using modified generalized symmetry transform and image warping,” Proc. of IEEE International Symposium on Industrial Electronics, vol. 3, pp. 2022–2027, 2001.
[10]Dai Yan et al, “A high performance license plate recognition system based on the web technique,” IEEE Intelligent Transportation System Conference Proceedings, pp.325-329, 2001.
[11]Clemens Arth, Florian Limberger, and Horst Bischof, “Real-Time License Plate Recognition on an Embedded DSP-Platform,” Proc. of IEEE Conference on Computer Vision and Pattern Recognition (Embedded Computer Vision Workshop), Jun. 2007.
[12]P. Viola and M. Jones,“Robust real-time face detection,”International Journal of Computer Vision, vol. 57, no. 2, pp.137-154, 2004.
[13]Yoav Freund and Robert E. Schapire,“A decision-theoretic generalization of on-line learning and an application to boosting,”Journal of Computer and System Sciences, vol. 55, no. 1, pp.119-139, Aug 1997.
[14]C.C Chen, J.W. Hsieh, J.C. Wu and Y.S. Chen, “Detecting license plates from videos using morphological operations and Adaboosting algorithm,” Proceedings of International Computer Symposium, Taipei, Taiwan ROC, vol. 3, pp.1201-1204, Dec 2006.
[15]C.C Chen, J.W. Hsieh, J.C. Wu and Y.S. Chen, “License plate detection using morphological operations and adaboosting algorithm,” Proceedings of 19th IPPR Conference on Computer Vision, Graphics, and Image Processing, Taoyuan, Taiwan, ROC, pp. 958-965, Aug 2006.
[16]I-Chen Tsai, Jui-Chen Wu, Jun-Wei Hsieh and Yung-Sheng Chen, “Recognition of vehicle license plates from a video sequence,” Proceeding of 21th IPPR Conference on Computer Vision, Graphics, and Image Processing, Aug. 24-26, 2008.
[17]C. Papageorgiou, M. Oren and T. Poggio, “A general framework for object detection,” International Conference in Computer Vision, pp.555-562, Jan 1998.
[18]M. Jones and P. Viola, “Fast multi-view face detection,” IEEE Conference on Computer Vision and Pattern Recognition, pp. 2, TR2003-96, July 2003.
[19]C.C. Chang and C.J. Lin. LIBSVM: a library for support vector machines, 2001. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm.
[20]K. Chamnongthai and T.Sirthinaphong, “Extraction of Car License Plate Using Motor Vehicle Regulation and Character Pattern Recognition,” Circuits and System, 1998 IEEE APPCCAS 1998. The 1998 IEEE Asia-Pacific Conference on, 1998, Page(s):559-562.
[21]C. Busch, R. Domer, C. Freytag, and H. Ziegler, “Feature Based Recognition of Traffic Video Streams for online Route Tracing,” Vehicular Technology Conference, 1998. VTC 98. 48th IEEE vol. 3, 1998, Page(s):1790-1794.
[22]Tran Duc Duan, Tran Le Hong Du, Tran Vinh Phuoc, Nguyen Viet Hoang, “Build an automatic vehicle license-plate recognition system,” Intl. Conf. in Computer Science-RIVF, pp.59-63, 2005.
[23]Kamat, Varsha, and Ganesan, “An Efficient Implementation of the Hough Transform for Detecting Vehicle License Plate Using DSP’S,” Proceedings of Real-Time Technology and Application, pp.58-59, 1995.
[24]Yanamura. Y, et al, “Extraction and Tracking of the License Plate using Hough Transform and Vote Block Matching,” Proceedings of IEEE Intelligent Vehicles Symposium, pp.243-246, June 2003.
[25]S.H. Park, K.I. Kim, K. Jung, H.J. Kim, “Locating Car License Plates Using Neural Network,” Electronics Letters, vol.35, No.17, pp.1475-1477, 1999.
[26]W.G. Zhu, G.J. Hou, X. Jia, “A Study of Locating Vehicle License Plate Based on Color Feature and Mathematical Morphology,” Signal Processing, vol.1, pp.748-751, 2002.
[27]Texas Instrument, Inc. “DM644x DaVinci™ Technology Workshop,” Revision 0.95., February 2007.
[28]Texas Instrument, Inc. “DVEVM Getting Started Guide,” Literature Number: SPRUE66, March 2006.
[29]Texas Instrument, Inc. “TMS320DM6446 Digital Media System-on-Chip,” Literature Number: SPRS283E, March 2007.
[30]Texas Instrument, Inc. “Codec Engine Application Developer User’s Guide,” Literature Number: SPRUE67D, September 2007.
[31]Texas Instrument, Inc. “Codec Engine Server Integrator’s Guide,” Literature Number: SPRUED5, July 2006.
[32]Texas Instrument, Inc. “eXpress Dsp Components (XDC) toolset,” Component Tools, 2004.
[33]Texas Instrument, Inc. “Mastering the Art of Memory Map Configuration for DaVinci-Based Systems,” Literature Number: SPRAAQ6, September 2007.
[34]Texas Instrument, Inc. “TMS320C6000 Optimizing Compiler v 6.1 User’s Guide,” Literature Number: SPRU187O, May 2008.
[35]Texas Instrument, Inc. “TMS320C6000 Programmer’s Guide,” Literature Number: SPRU198I, March 2006.
[36]Texas Instrument, Inc. “Hand-Tuning Loops and Control Code on the TMS320C6000,” Literature Number: SPRA666, August 2006.