臺灣博碩士論文加值系統

隨著智慧型手機的普及，幾乎人手一機，且機不離身。本文研發一套自動中文名片辨識APP，本系統可以解決傳統名片在使用上和攜帶上的不便性。
本系統主要包括5個步驟，第一步是從攝影機拍到的實際影像進行名片的4個頂點偵測；第二步是以偵測到的4個頂點進行透視轉換，目的是完成名片的幾何校正，使校正後的名片形狀是矩形；第三步是在校正後的名片上進行文字偵測，並且合併所有類似的文字區域，目的是有利於後續文字辨識後的資訊後處理；第四步是進行影像文字辨識前處理及進行辨識；第五步是進行辨識後的資訊後處理，分別取得中文名字、EMAIL、及電話號碼。本系統可解決傳統名片在使用上和攜帶上的不便。
不僅如此，因為Android系統的智慧型手機是目前市占率最高的系統，本研究以Android系統為研發平臺開發中文名片APP。為了加快運算速度，以及使用Intel的電腦視覺函式庫OpenCV，本研究以混合Android SDK技術與NDK技術進行中文名片APP系統開發。從智慧型手機拍攝照片到中文名片辨識，最後將中文名字、EMAIL、及電話號碼加入智慧型手機電話簿中以方便未來使用。實驗證明，本文提出的中文名片辨識系統有不錯的辨識效能，達到90%的正確率，不僅如此，對於實際應用上也有不錯的強健性。

This paper proposes an automatic Chinese business card recognition system including 5 operation steps. Firstly, four corners detection should be done on the captured image. Secondly, the detected four corners are used to perform perspective transformation for square business card image. Thirdly, text detection is applied to extract text regions. Additionally, to make information processing easy, we propose to merge the related text regions. Fourthly, text region preprocessing and recognition are performed. Finally, the post-processing is necessary for extracting Chinese name, EMAIL, and phone number. We have built a Chinese Business Card App on the Android plateform with OpenCV library for Android. Experiments carried out on the realistic image from camera have shown that the proposed method achieves good recognition performance up to 90% and possesses high robust to realistic scenarios.

謝誌 I
中文摘要 II
目次 IV
圖目錄 VI
表目錄 VII
第一章、緒論 1
第二章、Android系統及開發簡介 5
第三章、相關研究探討 13
第四章、研究方法 16
第五章、實驗結果 34
第六章、結論 41
參考文獻 42
附錄1-1 PC版名片辨識範例1 45
附錄1-2 PC版名片辨識範例2 46
附錄1-3 PC版名片辨識範例3 47
附錄1-4 PC版名片辨識範例4 48
附錄2 實驗用前15張樣本 49
附錄3 實驗用後15張樣本 50
附錄4 本實驗APP辨識結果(幾何失真) 51
附錄5 名片全能王APP辨識結果(幾何失真) 52
附錄6 蒙恬名片王APP辨識結果(幾何失真) 53
附錄7 本研究APP辨識結果(燈光變化) 54
附錄8 名片全能王APP辨識結果(燈光變化) 54
附錄9 蒙恬名片王APP辨識結果(燈光變化) 55
附錄10本研究APP辨識結果(手拿名片) 55
附錄11 名片全能王APP辨識結果(幾何失真) 56
附錄12 蒙恬名片王APP辨識結果(幾何失真) 56

[1] http://iknow.stpi.narl.org.tw/post/Read.aspx?PostID=9996
[2] Faruk, M. A., Nabamita, M., Subhadip, B., Mita, N. (2011), Design of an optical character recognition system for camera based handheld devices. International Journal of Computer Science Issues, 2011, Vol.8, No.4 , pp 283-289, 2011.
[3] Luo, X.-P., Li, J., and Zhen, L.-X. (2004). Design and implementation of a card reader based on build-in camera. International Conference on Pattern Recognition, pp. 417-420, 2004.
[4] Luo, X.-P., Zhen, L.-X., Peng, G., Li J. and Xiao, B.-H. (2005). Camera based mixed-lingual card reader for mobile device. International Conference on Document Analysis and Recognition, pp. 665-669, 2005.
[5] Niblack, W. (1986), An Introduction to Digital Image Processing. Prentice/Hall International. 1986.
[6] Otsu, N. (1979). A Threshold Selection Method from Gray-Level Histograms. IEEE Transactions on Systems, Man, and Cybernetics. 1979. SMC-9(1), 62-66, 1979.
[7] Pan, W., Jin, J., Shi, G., Wang, Q. R. (2001). A system for automatic Chinese business card recognition. Proc. ICDAR-01, 2001, pp.577-581.
[8] Sauvola, J., Seppanen, T., Haapakoski, S., and Pietikainen. M. (1997). Adaptive Document Binarization. In International Conference on Document Analysis and Recognition, volume 1, pages 147–152, 1997.
[9] Shen, H. and Coughlan, J. (2006), Reading LCD/LED Displays with a Camera Cell Phone. Proceedings of the 2006 Conference on Computer Vision and Pattern Recognition Workshop, 2006.
[10] Wolf, C., Jolion, J.-M., and Chassaing, F. (2002). Text Localization, Enhancement and Binarization in Multimedia Documents. In Proc. of the International Conference on Pattern Recognition (ICPR), volume 4, pp. 1037-1040, 2002.
[11] Hough, P. V. C. (1962). Method and means for recognizing complex patterns, U.S. Patent 3069654. 1962.
[12] Duda, R. O., Hart P. E. (1975). Use of the Hough transform to detect lines and curves in pictures. Communs Ass. Comput. Match. pp. 11-15. 1975.
[13] Ballard, D. H. (1981). Generalizing the Hough transform to detect arbitrary patterns. Pattern Recognition. pp. 111-122. 1981.
[14] Matas, J., Galambos, C., and Kittler, J. (2000). Robust detection of lines using the progressive probabilistic Hough transform. Computer Vision and Image Understanding, pp. 119–137, April 2000.
[15] http://en.wikipedia.org/wiki/Android_(operating_system).
[16] http://zh.wikipedia.org/wiki/Android.
[17] http://en.wikipedia.org/wiki/Comparison_of_optical_character_recognition_software
[18] https://code.google.com/p/tesseract-ocr/
[19] http://www.abbyy.com/
[20] http://office.microsoft.com/zh-tw/onenote-help/HA103465577.aspx
[21] Cai, M., Song, J., and Lyu, M. R. (2002). A New Approach for Video Text Detection. Proc. of IEEE Int’l Conference on Image Processing. pp. 117-120. 2002.
[22] Jain, A. K., and Yu, B. (1998). Automatic Text Location in Images and Video Frames. Pattern Recognition 31(12). pp. 2055-2076. 1998.
[23] Agnihotri, L., and Dimitrova, N. (1999). Text Detection for Video Analysis. Proc. of Int’l Conf. on Multimedia Computing and Systems. pp. 109-113. 1999.
[24] Gllavata, J., Ewerth, R., and Freisleben, B. (2003). A Robust Algorithm for Text Detection in Images. Proc. of 3rd Int'l Symposium on Image and Signal Processing and Analysis. pp. 611-616. 2003.
[25] Hao, Y., Yi, Z., Zengguang, H., and Min, T. (2003). Automatic Text Detection In Video Frames Based on Bootstrap Artificial Neural Network and CED. Journal of WSCG Vol. 11. No.1. Plzen. Czech Republic. 2003.
[26] Li, H., Doermann, D., and Kia, O. (2000). Automatic Text Detection and Tracking in Digital Videos. IEEE Transactions on Image Processing. Vol. 9. No. 1. pp. 147-156. 2000.
[27] Wu, V., Manmatha, R., and Riseman, E. M., (1999). Textfinder: An Automatic System to Detect and Recognize Text in Images. IEEE Transactions on Pattern Analysis and Machine Intelligence. Vol. 21. Issue 11. pp. 1224-1229. 1999.
[28] Lienhart, R., and Wernicke, A., (2002). Localizing and Segmenting Text in Images and Videos. IEEE Transactions on Circuits and Systems for Video Technology. Vol. 12. No. 4. pp. 256-268. 2002.
[29] http://opencv.org/downloads.html
[30] https://developer.android.com/tools/sdk/ndk/index.html
[31] http://en.wikipedia.org/wiki/Line%E2%80%93line_intersection
[32] http://docs.opencv.org/doc/tutorials/imgproc/imgtrans/canny_detector/canny_detector.html
[33] http://docs.opencv.org/doc/tutorials/imgproc/imgtrans/hough_lines/hough_lines.html
[34] http://docs.opencv.org/modules/imgproc/doc/geometric_transformations.html
[35] http://docs.opencv.org/doc/tutorials/imgproc/opening_closing_hats/opening_closing_hats.html