臺灣博碩士論文加值系統

財政部為了防止逃漏稅，於民國77 年11 月開始施行統一發票給獎辦法，鼓勵民眾拿取發票來增加額外的收入，許多的慈善團體也將募集發票視為一個重要的財源，但人工逐一目視對獎發票的動作相當單調。將兩個月所累積下來的發票總量與多組中獎數字進行交叉比對，耗時又耗力。如果透過電腦能將對獎的流程一貫化，則可大幅的降低使用者的負擔。本論文所研究之統一發票自動對獎系統(automatic invoice winning system )使用階層式模組化C 語言搭配OpenCV 函式庫(Open Source Computer Vision Library)，實現於一般的家用個人電腦。針對各種不同的角度、光線，還有各種不同深淺樣式浮水印的發票情形，利用一般家用的USB 個人電腦攝影機(PC Camera)，搭配簡單的背景，以影像處理的方式自動偵測目標發票，並辨識出發票上的對獎數字，將對獎的動作變成由電腦執行影像辨識的一貫化的流程。實驗結果顯示系統可以每秒27 偵的速度進行即時發票自動偵測，並容許360 度的任意歪斜角度，98.63%的高精準度能正確的篩選出各種顏色與紋路的浮水印背景下的中獎發票，每一張發票由取像到辨識出數字平均運算時間為114ms，達到提升對獎的效率與降低人力消耗的目標。

In order to prevent the tax invasion problem for the Ministry of finance, they encouraged people to receive the invoice to established extra incomes from the beginning of the rewarding method of uniform invoice a in November, 77 in Republic of China. That is also one of the most important financial resources for many charitable organizations. However, check the award-winning list one by one in artificial was pretty monotone. It’s not only time-consuming but also tedious for the cross match between the totally invoice accumulated in two months and many pair of award-winning numbers. If we can make the procedure consistent in checking number through computers, that could lower the user’s burden in speed step. The automatic invoice winning system in this theory with Open Source Computer Vision Library was used in personal computer. To every kinds of counters, including angles, lights, and different types of watermarks, it make good used of computer USB and PC Camera of personal computer with simple background. The way of using image-processing to auto-detect the target receipt, and distinguish the compared number on the receipt has made the reward-checking become a constant process of visual distinguishing done by computer. The experiment has showed out that the system can processing the receipt immediately at the speed of 27 frames per second, 360 degree of willful angle allowed, and with the 98.63 percent of high precision can select any kind of color and vein under the watermark’s background of the winning ticket; each of the receipt’s average time of calculation from vision-selection to distinguish the number is 114 ms, achieving the goal of lifting efficiency while checking ticket and lower the consumption of personal.

口試委員審定書 .................................................................................................................... i
誌謝 ....................................................................................................................................... ii
中文摘要 .............................................................................................................................. iii
英文摘要 .............................................................................................................................. iv
第一章緒論 ..........................................................................................................................1
1.1 研究背景與動機 .....................................................................................................1
1.2 文獻回顧 .................................................................................................................4
1.3 章節組織 .................................................................................................................10
第二章系統與場景環境 .....................................................................................................11
2.1 問題與挑戰 .............................................................................................................11
2.2 開發環境 .................................................................................................................13
2.3 操作情境設計 .........................................................................................................15
2.3.1 物距範圍 ......................................................................................................15
2.3.2 背景樣式選定 ...............................................................................................17
2.3.3 發票放置方式 ..............................................................................................19
2.4 模組化程式設計 ......................................................................................................20
2.4.1 影像座標系統 ..............................................................................................20
2.4.2 資料結構訂定 ...............................................................................................21
2.4.3 專案檔案階層化模組結構圖 .......................................................................23
第三章統一發票對獎系統演算法 .....................................................................................25
3.1 影像處理背景知識 .................................................................................................25
3.1.1 灰階圖像 .......................................................................................................25
3.1.2 邊緣偵測 .......................................................................................................26
3.2 移動發票的目標物自動偵測 ...............................................................................27
3.2.1 背景影像相減法 ...........................................................................................29
3.2.2 時序影像差值計算法 ...................................................................................30
3.2.3 背景差與前景差混合偵測法 .......................................................................32
3.2.4 整體移動發票自動目標物偵測演算法 .......................................................35
3.3 前處理模組 .............................................................................................................37
3.3.1 旋轉發票 .......................................................................................................38
3.3.1.1 平行線偵測法 ...................................................................................38
3.3.1.2 角度校正 ...........................................................................................41
3.3.1.3 旋轉 ...................................................................................................42
3.3.3 影像增強 ......................................................................................................44
3.3.3.1 Otsu 淡化 ...........................................................................................44
3.3.3.2 sin 影像增強 ......................................................................................46
3.3.4 二值化 ..........................................................................................................47
3.3.4.1 Otsu 二值化 .......................................................................................48
3.3.4.2 適應性發票二值化 ...........................................................................49
3.4 數字切割 .................................................................................................................52
3.5 錯誤校正 .................................................................................................................56
3.5.1 前處理校正 ...................................................................................................56
3.5.2 旋轉校正 .......................................................................................................57
3.6 數字辨識 .................................................................................................................58
3.6.1 正規化 ..........................................................................................................59
3.6.2 辨識特徵擷取 ...............................................................................................60
3.6.3 圖片分類 .......................................................................................................62
3.6.3.1 樣版取樣法 ........................................................................................62
3.6.3.2 最小距離法 ........................................................................................64
3.6.3.3 最大相似法 ........................................................................................65
3.6.3.4 階段式樣版比對法 ...........................................................................66
3.7 發票對獎方法 .........................................................................................................68
3.7.1 對獎清單格式 ...............................................................................................71
第四章實驗結果與分析 .....................................................................................................72
4.1 不同角度 ..................................................................................................................73
4.2 不同公司行號 ..........................................................................................................74
4.3 不同高度 ..................................................................................................................74
4.4 不同顏色與樣式發票 .............................................................................................76
4.5 不同深淺浮水印變化 ..............................................................................................77
4.6 不同程度的光線 ......................................................................................................81
4.7 辨識率 ......................................................................................................................83
4.8 皺折與特殊發票的效果 ..........................................................................................86
4.9 效能分析 ..................................................................................................................88
4.10 近年發票辨識論文比較 .......................................................................................90
第五章結論與未來展望 ...................................................................................................92
5.1 結論 .........................................................................................................................92
5.2 未來展望 .................................................................................................................93
參考文獻 ...............................................................................................................................95

[1] 統一發票對獎網, http://invoice.easylife.tw/
[2] 曾麗清,統一發票處理裝置”,M388676
[3] 羅進良,統一發票之掃描對獎裝置”,M389404
[4] Desa, S. M. and Salih, Q. A., “Image subtraction for real time moving object extraction,” Proc. of IEEE International Conference on Computer Graphics, Imaging and Visualization, Penang, pp. 41-45,2004
[5] Cucchiara,R., Grana, C., Piccardi, M. and Prati, A., “Detecting Moving Objects, Ghosts, and Shadows in Video Streams,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 10, October,2003
[6] Tou, J.T., and Gonazalez, R.C., “Pattern Recognition Principles,” Addison-Wesley, Canada, Ch.3, pp.90-93. ,1974
[7] Ya, L., Haizho, A., and Guangyou, X., “Moving object detection and tracking based on background subtraction,” Proc. of SPIE- The International Society for Optical Engineering, Wuhan, Vol. 4554, pp.62-66,2001.
[8] 王俊明及陳世旺,“ 漸進背景影像的建構,” 師大學報： 數理與科技類,47(2),43-54,2002
[9] Cucchiara, R. , Grana, C. , Piccardi, M. Prati, A. Sirotti, S. , “Improving Shadow Suppression in Moving Object Detection with HSV Color Information,” 2001 IEEE Intelligent Transportation Systems Conference Proceedings - Oakland (CA), USA -August 25-29, 2001
[10] 林明毅, “多鏡頭視訊監控系統之前景區塊偵測與位元率分配機制,” 國立中央大學通訊工程研究所,碩士論文,2006
[11] Canny, J.F., “A computational approach to edge detection,” IEEE Trans Pattern Analysis and Machine Intelligence, 8(6): 679-698, Nov 1986.
[12] M.B. Ahmad and T.S. Choi,“Local Threshold and Boolean Function Based Edge
Detection,” IEEE Trans. Consumer Electron., vol. 45, No. 3, pp. 674-679, August 1999.
[13] Pierre D. Wellner, “Adaptive Thresholding for the DigitalDesk,” EuroPARC Technical Report EPC-93-110,1993
[14] N. Otsu, “A Threshold Selection Method from Gray-Level Histograms,” IEEE Trans. On System, Man and Cybernetics, vol. SMC-9, no. 1,pp.62-66, 1979.
[15] Yibing Yang, Hong Yan, “An adaptive logical method for binarization of degraded document images,” Pattern Recognition 33, pp. 787-807,2000
[16] Yu-Ting Pai, Yi-Fan Chang and Shanq-Jang Ruan, “Adaptive thresholding algorithm:Efficient computation technique based on intelligent block detection for degraded document images,” Pattern Recognition Volume 43, Issue 9, September 2010,p.3177-3187
[17] W. Niblack, “An Introduction to Digital Image Processing,” Pretice-Hall, Englewood Cliffs, NJ, 1986.
[18] J. Sauvola, M. Pietikainen, “Adaptive document image binarization,” Pattern Recognition 33 ,p.225–236,2000.
[19] P.V.C. Hough. “Method and Means for Recognizing Complex Patterns,” US Patent 3,069,654, December 1962
[20] 張弘儒、陳昀瑚、黃仲毅, “發票對獎系統,” 南台科技大學實務專題,2007
[21] 黃偉銓, “應用影像處理技術於統一發票之號碼自動辨識,” 臺灣科技大學高分子工程系,碩士論文, 2008
[22] H. L. Bai, J. M. Zhu and C. P. Liu, “A fast license plate extraction method on complex background,” in Proc. IEEE Intelligent Transportation Systems, vol. 2, pp.985-987, Oct. 2003.
[23] Shyang-Lih, Li-Shien Chen, Yun-Chung Chung, and Sei-Wan Chen, “Automatic license plate recognition,” IEEE Transaction on Intelligent Transportation Systems, vol.5, pp.42-53,2004.
[24] Cheng, Y., Lu, J., Yahagi, T., “Car License Plate recognition based on the Principal Components Analysis and Radial basis Function Networks,” Proceedings of the IEEE international Conference on Signal Processing(ICSP `04), Vol. 2, pp. 1455-1458, 2004.
[25] W. G. Zhu, G. J. Hou and X. Jia, “A study of locating vehicle license plate based on color feature and mathematical morphology,” in Proc. IEEE International Conference on Signal Processing, vol.1, pp. 748-751, 2002.
[26] C. Coetzee, C. Botha and D. Weber, “PC based number plate recognition system,” in Proc. IEEE Symposium on Industrial Electronics, vol. 2, pp. 605-610, July 1998.
[27] 王中山, “使用小波轉換於車牌偵測,” 國立中山大學機械與機電工程研究所, 碩士論文, 2004.
[28] Parisi R., Di Claudio E.D., Lucarelli G., Orlandi G., “Car plate recognition by neural networks and image processing,” Proceedings of the 1998 IEEE international Symposium on Circuits and Systems, Vol.3, pp.195-198, 1998.
[29] C. A. Rahman, W. Badawy and A. Radmanesh, “A real time vehicle's license plate recognition system,” in Proc. IEEE Conference on Advanced Video and Signal Based Surveillance, pp. 163-166, July 2003.
[30] H. A. Hegt, R. J. de la Haye and N. A. Khan, “A high performance license plate recognition system,” in Proc. IEEE International Conference on Systems, Man, and Cybernetics, vol. 5, pp.4357-4362, Oct. 1998.
[31] Oivind Due Trier , Anil K. Jain, and Torfinn Taxt, “Feature extraction methods for character recognition-A survey,” Pattern Recognition, Vol. 29, No. 4, pp. 641-662,1996.
[32] 李健宏, “植基於WGLVQ離線式手寫數字辨識,” 台灣師範大學工業教育學系,在職進修碩士論文, 2003
[33] Gunilla Borgefors, “Distance Transformations in Digital Images,” Computer Vision, Graphics, and Image Processing 34, 344-371 ,1986
[34] Choudhury A. Rahman, Wael Badawy, Ahmad Radmanesh, “A Real Time Vehicle’s License Plate Recognition System,” avss, 2003 IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS'03), pp.163, 2003.
[35] M. A. Ko and Y. M. Kim, “License plate surveillance system using weighted template matching,” in Proc. The 32nd Applied Imagery Pattern Recognition Workshop, pp.269-274, Oct. 2003.
[36] A. Khotanzad and Y. H. Hong, “Invariant image recognition by Zernike moments,” IEEE Trans. Pattern Anal. Mach. lntell. 12(5), 489-497 (1990).
[37] 方建中, “利用結構式特徵在多層次架構做光學字元辨識,” 國立中央大學資訊工程研究所, 碩士論文, 2001.
[38] A. S. Pandya, R. B. Macy, “Pattern Recognition with Neural Networks in C++,” CRC Press & IEEE Press, 1996.
[39] R.Schapire and Y. Singer, “A BoostTexter: A Boosting-Based System for Text Categorization,” Machine Learning, vol 39, pp. 135-168, May, 2000.
[40] A. Torralba, K. P. Murphy, and W. T. Freeman, “Sharing Visual Features for Multiclass and Multiview Object Detection,” IEEE Trans. on PAMI, Vol. 29, pp.846-869, May, 2007.
[41] 林家緯, “以統計數據為基礎的車牌影像處理與辨識方法,” 中山大學機械與機電工程研究所,碩士論文,2006
[42] Yoav Freund ,Robert E. Schapire, “A Short Introduction to Boosting ,” Journal of Japanese Society for Artificial Intelligence, 14(5):771-780, September, 1999.
[43] 賴鼎宇, “使用嵌入式linux 發展電腦視覺系統之研究,” 義守大學資訊工程研究所,碩士論文, 2006
[44] 邱郁淑, “高準確度統一發票號碼辨識系統與實作,” 義守大學資訊工程研究所, 碩士論文, 2010
[45] Rafael C. Gonzalez & Richard E. Woods, “Digital Image Processing, 3rd ed,” Pearson Education Taiwan, 2008, p.165-171
[46] K. Engel., “Real-time volume graphics,” pp.112–114, 2006.
[47] Scharr and Hanno, “Optimal Operators in Digital Image Processing,” Dissertation (in German),2000 .
[48] Azuma, “A Survey of Augmented Reality Presence: Teleoperators and Virtual Environments,” pp. 355-385, August 1997
[49] 王世君, “多模組整合人物偵測追蹤系統,” 東華大學資訊工程學系研究所,碩士論文,2003
[50] Arfken, G., “Mathematical Methods for Physicists, 3rd ed.,” Orlando, FL: Academic Press, 1985.
[51] 陳翔傑, “自動化車牌辨識系統設計,” 國立中央大學電機工程研究所,碩士論文,2005
[52] 財政部稅務入口網, http://www.etax.nat.gov.tw