臺灣博碩士論文加值系統

文件分析與辨識之研究行之已久，應用十分廣泛，在數位化過程中扮演十分重要的角色。最常用的方法是採用體積龐大的桌上型掃瞄器，經過耗時的文件掃瞄等待，透過有線連接將影像資料傳送給電腦端的套裝應用軟體來進行處理、分析、辨識以及備份。
為了增進這個應用的效率與方便性，本論文提出一種低成本又便於攜帶的英文平面印刷刊物文章段落之取像架構，然後導入快速辨識之演算法於數位信號處理器內實現，感興趣範圍的辨識結果則顯示在液晶螢幕上，並透過藍牙資料傳輸的技術，將辨識結果同步上傳至電腦端。這些辨識結果的資料可以提供給電腦端未來相關應用之使用。大量之實驗結果顯示本論文所提之架構可快速且正確辨識不同之英文平面印刷刊物文章段落。

The research of document analysis and recognition is put into practice for long time and applied popularly. It plays the leading role in the digitalization process. The commonest way is that it makes use of a flatbed scanner with big size via a long waiting of document scanning and then transmits the image data to PC (Personal Computer) simultaneously via a wired connection. The transmitted images are used in advanced processing, analysis, recognition as well as back-up of a suite of application program.
In order to improve the efficiency and convenience of the application, the thesis proposes a low cost and portable opto-mechanism to grab the article or the paragraph of English machine printed publication. Furthermore, the algorithms of fast recognition are implemented on DSP (Digital Signal Processer). The recognition results of ROI (Region of Interest) are not only displayed on a LCD (Liquid Crystal Display) monitor but also transmitted to PC via data transmission technology of Bluetooth. These data of the recognition results can provide PC with the usage of relevant applications in the future. Finally, an amount of experimental results verify that the proposed recognition system can rapidly and correctly recognize the article or the paragraph of English machine printed publication.

中文摘要 i
ABSTRACT ii
誌謝 iv
TABLE OF CONTENTS v
LIST OF TABLES viii
LIST OF FIGURES ix
CHAPTER 1 INTRODUCTION 1
1.1 Motivation 1
1.2 Literature review 2
1.3 Study objective 4
1.4 Thesis organization 10
CHAPTER 2 IMAGE PREPROCESSING 11
2.1 Video capture 11
2.2 Converting YCbCr to RGB image 11
2.3 Converting RGB to gray image 11
2.4 Converting gray to binary image 12
2.5 Blob analysis 14
2.5.1 Pixel connectivity 14
2.5.2 Connected-component labeling 17
2.6 Cleaning border objects 18
2.7 Removing noises and small objects 18
2.7.1 Bounding box of each blob 18
2.7.2 The threshold of noises and small objects 19
2.7.3 The area of each blob 19
CHAPTER 3 IMAGE ORIENTATION CORRECTION 20
3.1 Skew angle detection 20
3.1.1 Dilation and erosion 20
3.1.2 Orientation angle 21
3.1.3 Filling holes 22
3.2 Image skew correction 23
CHAPTER 4 SEGMENTATION AND FEATURE EXTRACTION 25
4.1 Text line segmentation 25
4.2 Word segmentation 27
4.3 Contour tracing 28
4.3.1 Purpose 29
4.3.2 Method 29
CHAPTER 5 RECOGNITION 31
5.1 Fourier descriptor 31
5.2 Linear interpolation 33
5.3 Template matching 34
5.4 Similarity measurement 35
5.5 Image flip 35
CHAPTER 6 BLUETOOTH OVERVIEW 36
6.1 Basics 36
6.1.1 Specification make-up 38
6.1.2 Spectrum 39
6.1.3 Interference 39
6.1.4 Range 39
6.1.5 Power 40
6.1.6 Data rate 40
6.1.7 Piconet 40
6.2 Bluetooth SIG 41
6.3 Serial port profile 41
6.3.1 Scope 42
6.3.2 Usage scenarios 42
6.3.3 Roles 42
CHAPTER 7 SIMULATION AND IMPLEMENTATION TOOLS 44
7.1 MATLAB/Simulink 44
7.2 Aptina Imaging NTSC/PAL CMOS image sensor 44
7.2.1 Composite video as NTSC vs. PAL 45
7.2.2 Aptina Imaging CMOS image sensor MT9V136 47
7.3 TEXAS INSTRUMENTS TMS320DM6437 digital video
development platform 51
7.4 TEXAS INSTRUMENTS CCStudio v3.3 IDE 54
7.5 IVT BlueSoleil software and Qcom Bluetooth module 55
7.5.1 IVT BlueSoleil 5.4.280.1 55
7.5.2 Operation procedure of IVT BlueSoleil 56
7.5.3 Qcom QBTM400 and QBTM500(I) Bluetooth module 60
7.6 IVT Hyper terminal settings 63
CHAPTER 8 EXPERIMENTAL RESULTS 66
8.1 Simulation results 66
8.2 Implementation results 68
8.2.1 Hardware structure 72
8.2.2 Simulink model 72
8.2.3 Model-based design 77
8.2.4 Using embedded MATLAB 78
8.2.5 Embedded MATLAB subset 79
8.2.6 Real-time workshop 79
8.2.7 Embedded IDE Link with Texas Instruments Code
Composer Studio 80
8.2.8 Video and image processing blockset 80
8.2.9 Dm6437evmlib blockset 80
8.2.10 Recognition results 81
CHAPTER 9 CONCLUSION 85
REFERENCE 87
NOMENCLATURE 92

[1] P. Lyman and H. R. Varian, "How Much Information," Technical Report retrieved from http://www2.sims.berkeley.edu/research/projects/how-much- info-2003/, 2003.
[2] S. Marinai, "Introduction to Document Analysis and Recognition," Machine Learning in Document Analysis and Recognition, Springer-Verlag Berlin Heidelberg, 2008, pp.1-20.
[3] Penpower Technology Ltd., "Optical Recognition," Technical Informations retrieved from http://www.penpower.com.tw/technology-OCR.asp.
[4] S. Impedovo, R. Modugno, A. Ferrante and E. Stasolla, "New Trends in Digital Scanning Processes," 10th International Conference on Document Analysis and Recognition, 2009, pp.1071-1075.
[5] D. Doermann, J. Liang and H. Li, "Progress in Camera-Based Document Image Analysis," Proceedings of the Seventh International Conference on Document Analysis and Recognition, vol.1, 2003, pp.606-616.
[6] A. J. Park and K. C. Jung, "Intelligent Document Scanning with Active Camera," Proceedings of the Eight International Conference on Document Analysis and Recognition, vol. 2, 2005, pp.991-995.
[7] C. T. Zahn and R. Z. Roskise, "Fourier Descriptors for Plane Closed Curves," IEEE Transactions on Computers, vol.c-21, no.3, 1972, pp.269-281.
[8] Ø. D. Trier, A. K. Jain and T. Taxt, "Feature Extraction Methods for Character Recognition-A Survey," Pattern Recognition, vol.29, no.4, 1996, pp.641-662.
[9] C. S. Jeong and D. S. Jeong, "Hand-Written Digit Recognition Using Fourier Descriptors and Contour Information," TENCON 99 Proceedings of the IEEE Region 10 Conference, vol.2, 1999, pp.1283-1286.
[10] H. T. Jia and M. Xie, "Improvement of Fourier Descriptor Using Spatial Normalization," IEEE International Symposium on Communications and Information Technology, vol.2, 2005, pp.1284-1287.
[11] C. W. Yeh, In-tray LCD Driver IC Defect Inspection, Master Thesis, Graduate Institute of Automation Technology, National Taipei University of Technology, 2007.
[12] Z. D. Lu, R. Schwartz, P. Natarajan, I. Bazzi and J. Makhoul, "Advances in the BBN BYBLOS OCR System," Proceedings of the Fifth International Conference on Document Analysis and Recognition, 1999, pp.337-340.
[13] H. I. Avi-Itzhak, T. A. Diep and H. Garland, "High Accuracy Optical Character Recognition Using Neural Networks with Centroid Dithering," IEEE Transaction on Pattern Analysis and Machine Intelligence, vol.17, issue2, 1995, pp.218-224.
[14] 劉孝忠，Microcanonical平均退火類神經網路在晶片印字辨識之應用，第七屆人工智慧與應用研討會 (TAAI2002)，Image Processing (I) B5-3，2002，第408-413頁。
[15] H. Rau, J. W. Tzeng and L. P. Lu, "Automated Inspection of IC Printed Mark Defect (I) – Character," Recognition Journal of the Chinese Institute of Industrial Engineers, vol.20, no.4, 2003, pp.317-326.
[16] I. J. Kim and J. H. Kim, "Statistical Character Structure Modeling and Its Application to Handwritten Chinese Character Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.25, issue11, 2003, pp.1422-1436.
[17] The MathWork Inc., MATLAB R2010a Technical Document, Massachusetts USA, 2010.
[18] N. Otsu, "A Threshold Selection Method from Gray-Level Histograms," IEEE Transactions on Systems, Man and Cybernetics, vol.9, issue1, 1979, pp.62-66.
[19] A. G. Ghuneim, "Contour Tracing," Pattern Recognition Course retrieved from http://www.imageprocessingplace.com/downloads_V3/root_downloads/ tutorials /contour_tracing_Abeer_George_Ghuneim/index.html, 2000.
[20] R. M. Haralick and L. G. Shapiro, "Computer and Robot Vision," Volume I, Addison-Wesley, 1992, pp.40-48.
[21] J. Razjouyan, "BW Noise Reduction," Useful Code retrieved from MATLAB CENTRAL http://www.mathworks.com/matlabcentral/fileexchange/, 2006.
[22] J. K. Ha, R. M. Haralick and I. T. Phillips, "Recursive X-Y Cut Using Bounding Boxes of Connected Components," Proceedings of the Third International Conference on Document Analysis and Recognition, vol.2, 1995, pp.952-955.
[23] N. Liolios, N. Fakotakis and G. Kokkinakis, "Improved Document Skew Detection Based on Text Line Connected-Component Clustering," Proceedings of 2001 International Conference on Image Processing, vol.1, 2001, pp.1098-1101.
[24] B. V. Dhandra, V. S. Malemath, H. Mallikarjun and R. Hegadi, "Skew Detection in Binary Image Documents Based on Image Dilation and Region Labeling Approach," 18th International Conference on Pattern Recognition, vol.2, 2006, pp.954-957.
[25] L. C. Zhang, Y. Lu, G. Y. Chen and P. S. P. Wang, "Image Skew Detection for Formulas without Fraction Bars Using Connected Components Analysis," 7th IEEE International Conference on Computer and Information Technology, 2007, pp.680-679.
[26] G. S. Peake and T. N. Tan, "A General Algorithm for Document Skew Angle Estimation," Proceedings of International Conference on Image Processing, vol.2, 1997, pp.230-233.
[27] R. C. Gonzalez and R. E. Woods, "Morphological Image Processing," Digital Image Processing 2nd Edition, Prentice Hall Upper Saddle River New Jersey, 2002, pp.519-566.
[28] P. Soille, "Reconstruction based operators," Morphological Image Analysis: Principles and Applications 2nd Edition, Springer-Verlag Berlin Heidelberg New York, 2003, pp.208-209.
[29] D. S. Zhang and G. J. Lu, "A Comparison of Shape Retrieval Using Fourier Descriptors and Short-Time Fourier Descriptors," Proceedings of the Second IEEE Pacific Rim Conference on Multimedia, vol.2195, 2001, pp.855-860.
[30] D. S. Zhang and G. J. Lu, "A Comparative Study on Shape Retrieval Using Fourier Descriptors with Different Shape Signatures," Journal of Visual Communication and Image Representation, vol.14, no.1, 2003, pp.41-60.
[31] C. S. Chen, Image Geometry Transformation Supplements, Textbook in Digital Image Processing, Graduate Institute of Automation Technology, National Taipei University of Technology, 2006.
[32] C. H. Chen, The Study of Checking the Annual Inspection Status of Motorcycles Based on License Plate Recognition, Master Thesis, Department of Computer Science and Engineering, Tatung University, 2008.
[33] Bluetooth SIG, "Bluetooth Basics," Technical Informations retrieved from http://www.bluetooth.com/ or https://www.bluetooth.org/.
[34] TUV Rheinland Taiwan Ltd., Technical Document of Bluetooth Testing Service, 2009.
[35] Bluetooth SIG, Bluetooth Serial Port Profile Specification V12, 2001.
[36] R. C. Gonzalez, R. E. Woods, S. L. Eddins, Digital Image Processing using MATLAB 1st Edition, Prentice Hall, 2004.
[37] Wikipedia the free encyclopedia that anyone can edit, "Image Sensor," Technical Informations retrieved from http://en.wikipedia.org/wiki/Image_ sensor.
[38] Wikipedia the free encyclopedia that anyone can edit, "Composite Video," Technical Informations retrieved from http://en.wikipedia.org/wiki/Composite _video.
[39] Wikipedia the free encyclopedia that anyone can edit, "NTSC," Technical Informations retrieved from http://en.wikipedia.org/wiki/NTSC.
[40] Wikipedia the free encyclopedia that anyone can edit, "PAL," Technical Informations retrieved from http://en.wikipedia.org/wiki/PAL.
[41] C. B. Chuaong, "A Comparison and Study of NTSC, PAL and SECAM Color Television Systems," Journal of Nation Taiwan Normal University, vol.31, no.9, 1986, pp.225-292.
[42] H. F. Tzeng, The Development of Computer Vision Teaching Materials, Master Thesis, Department of Mechanical Engineering, National Pingtung University of Science and Technology, 2005.
[43] Aptina Imaging Corporation, MT9V136: 1/4-Inch Color CMOS NTSC/PAL Digital Image Sensor Data Sheet, 2008.
[44] Texas Instruments Incorporated., "DM6437 Digital Video Development Platform," Technical Informations retrieved from http://focus.ti.com/docs/ toolsw/folders/print/tmdsvdp6437.html.
[45] Texas Instruments Incorporated., "TMS320DM6437 Digital Media Processor," Technical Informations retrieved from http://focus.ti.com/docs/prod/folders/ print/tms320dm6437.html
[46] Texas Instruments Incorporated., "Code Composer Studio (CCStudio) Integrated Development Environment (IDE)," Technical Informations retrieved from http://focus.ti.com/docs/toolsw/folders/print/ccstudio.html.
[47] Qcom Technology Inc., QBTM400 Bluetooth 2.1+EDR USB Module Specification, 2008.
[48] IVT Corporation, "BlueSoleil," Technical Informations retrieved from http://www.ivtcorporation.com/.
[49] Qcom Technology Inc., QBTM500(I)_3A Bluetooth 2.1+EDR Class 2 Module Specification, 2009.
[50] Texas Instruments Incorporated., "Implementing Video Tracking Systems on DM6437 EVM using MATLAB and Simulink," Technical Informations retrieved from http://focus.ti.com/asia/download/TechDay09tw_DaVinci_track _9_DM6437_Esther_Wu_Terasoft.pdf.
[51] Texas Instruments Incorporated., "Implementing Video Tracking Systems on DM6437 EVM using MATLAB and Simulink," Technical Informations retrieved from http://focus.ti.com/download/tidc/pdfs/asia/2008/cn_T1_5 _Zhenggao _Xu_MathWorks.pdf.