臺灣博碩士論文加值系統

摘要
本論文研究的目的是透過光學字元辨識 (Optical Character Recognition, OCR) 的應用輔助年長者因為視覺的老化造成閱讀上的不便。所謂光學字元辨識技術就是分析並判讀一張影像上的文字，我們就是將這樣的技術應用在各種數位式健康量測儀器的數據判讀。
首先，透過攝像頭擷取儀器螢幕上的影像，接著利用影像前置處理程序強化影像品質。一般影像前處理程序包括，處理影像偏斜，影像正規化，將影像灰階化並調整對比度，標示基準線並切割影像…等等。若影像前置處理的程序處理不當，會直接影響後續的光學字元辨識的正確率。最後透過我們採用的光學字元辨識演算法分析及辨識取得影像的資訊。光學字元辨識演算法是依據每個字元特徵結構的不同，提取每個字元的特徵向量加以比較與辨識，以取得量測儀器所顯示的數據。使用本研究的方法實際進行阿拉伯數字的辨識測試，辨識結果有 97% 的正確率。
以我們的研究為基礎可以實現很多不同的應用。例如，實現人性化語音介面的數位式健康量測儀器；建構自動記錄與處理生理訊號的光學資訊閘道器，以達成個人健康管理；建立一個社區健康營造的創新互動媒介…等等。

Abstract
The goal of this study is that using applications of optical character recognition (OCR) technology assists the elder people whose visual is degraded by ageing. The OCR technique that is used for analysis and recognition of texts on an image can be applied to read out the information on the screen of digital healthcare measuring instruments.
At first, capture the image from the screen of the instrument. Subsequently, enhance the image quality by using image preprocessing procedures. General image preprocessing procedures include following items: normalize the image skew, convert the color image to a gray one or a binary one, adjust the contrast of the image, mark the baseline and portion the image, and so on. Finally, obtain the information of the image by OCR technology. Due to the different features of each character structure, extracted the feature vector of each character as the basis of the OCR procedure. Compare and recognize these features to extract the texts for beyond applications. Applying our method to recognize the photos of 0 to 9 digital, the recognition accuracy is 97%.
Based on our proposal, there are many different applications could be realized. For example, implement a friendly user interface by voice for digital healthcare measuring instruments, construct an optical information gateway for personal health management to record and handle physiological information automatically, create a novel interactive medium for community health formation… etc.

目錄
摘要
Abstract
誌謝
目錄
圖目錄
表目錄
第一章 緒論
1.1 研究背景
1.2 研究動機與目的
1.3 技術應用與相關文獻探討
1.3.1 影像前置處理
1.3.2 光學字元辨識
1.4 論文架構
第二章 理論探討
2.1 影像前置處理
2.1.1 色彩空間
2.1.2 二值化
2.1.4 影像細化演算法
2.2 字元辨識方法
2.2.1 統計法
2.2.2 結構法
2.2.3 類神經網路法
2.2.4 樣板比對法
2.3 系統建構
第三章 系統實現
3.1 系統分析
3.1.1 系統架構
3.1.2影像處理流程
3.2 影像前置處理的實現
3.2.1 灰階化
3.2.2 對比度增強
3.2.3 二值化
3.2.4 濾波
3.2.5 數據字元切割
3.2.6 細化
3.3 光學字元辨識演算法
3.4 後端應用的規劃
第四章 實驗結果與討論
4.1 影像前置處理的實驗結果
4.1.1 濾波
4.1.2 切割
4.1.3 細化
4.1.4 結論
4.2 光學字元辨識的實驗結果
4.2.1 多字元同時辨識
4.2.2 單一字元依序辨識
4.2.3 測試結果
4.2.4 雜訊抑制測試
第五章 結論與未來展望
5.1 結論
5.2 未來展望
參考文獻

參考文獻
[1] 內政部統計處, “http://www.moi.gov.tw/stat/index.aspx”.
[2] 凡鎧儀器有限公司,“http://www.fankai.com.tw/tonometer.html”.
[3] 松威醫療糖尿病服務中心, “http://shop.ek21.com/sunway/index.php”.
[4] 富康世界醫療器材用品中心, “http://fuekan-world.com.tw/pro908.html”.
[5] 張宏林, “Visual C++數位影像模示識別技術及工程實踐”, 文魁出版社, 2008.
[6] A. B. Cambra, A. C. Murillo, “Towards Robust and Efficient Text Sign Reading from a Mobile Phone ”. IEEE International Conference on Computer Vision Workshops, 2011.
[7] Lin Luo, Hao Sun, Weiping Zhou, Limin Luo, “An Efficient Method of License Plate Location”. IEEE, 2009.
[8] 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, 2006.
[9] A. S. Pandya, R. B. Macy, “Pattern Recognition with Neural Networks in C++”, CRC PRESS &; IEEE PRESS, 1996.
[10] R. C. Gonzalz, and R. E. Woods “Digital Image Processing”, Addison-Wesley, 1992.
[11] 周俊男, “車輛牌照影像辨識系統”, 中山大學, 1995.
[12] F. Lisa, J. Carrabina, C. Perez-Vicente, N. Avellana, and E. Valderrama, “Two-bit Weights Are Enough To Solve Vehicle License Recognition Problem”, IEEE International Conference on Neural Networks, vol.3, pp.1242-1246, 1993.
[13] A. Kertesz, V. Kertesz, T. Muller, “An On-Line Image Processing System for Registration Number Identification”, IEEE International Conference on Neural Networks, vol.6, pp. 4145-4148, 1994.
[14] R. Parisi, Di Claudio, G. Lucarelli, and G. Orlandi, “Car Plate Recognition by Neural Networks on Circuits and Image Processing”, Proceedings of the 1998 IEEE International Symposium on Circuits and Systems, vol. 3, pp. 195-198, 1998.
[15] M. Raus, and L. Kreft, “reading car license plates by the use of artificial neural networks”, Proceeding of the 38th Midwest Symposium on Circuits and Systems, vol. 1, pp. 538-541, 1996.
[16] Rakhi P. Ghugardare, Sandip P. Narote, P. Mukherji, Prathamesh M. Kulkarni, “Optical Character Recognition System for Seven”, IEEE, 2009.
[17] L. A. Torres-Méndez, J. C. Ruiz-Suárez, Luis E. Sucar, and G. Gómez, “Translation, Rotation, and Scale-Invariant Object”, IEEE Transactions on Systems, 2000.
[18] Mi-Ae Ko, Young-Mo Kim, “A simple OCR method from strong perspective view”, IEEE, 2004.
[19] N. Otsu, “A Threshold Selection Method from Gray-Level Histogram”, IEEE Trans. Syst., Man, Cybern., vol. 9, pp. 62–66, 1979.
[20] R. M. Haralick, S. R. Stenberg, and X. Huang, “Image Analysis Using Mathematical Morphology”, IEEE Trans. Pattern Anal, vol. 9, pp. 532–550, 1987.
[21] 莊志鴻, “以WMMS法做車牌字元辨識”, 交通大學, 1996.
[22] 楊文宗, “車輛牌照號碼自動辨識系統”, 中原大學, 1996.
[23] 張銘豪, “利用分割辨識方法之英文數字辨識系統”, 中山大學, 1996.
[24] R. Parisi, Di Claudio, G. Orlandi, and B. D. Rao, “A Generalized Learning Paradigm Exploiting the Structure of Feedforward Neural Networks”, IEEE Trans. On Neural Networks, vol.17, no.6, November 1996.
[25] C. J. Perez-Vicente, J. Carrabina, and E. Valderrama, “Discrete Learning in Feed-Forward Neural Networks”, International Journal on Neural Systems, vol.2, no.4, pp. 323-329, 1991.
[26] J. A. G. Nijhuis, M. H. Ter Brugge, K. A. Helmholt, J. P. W Pluim, L. Spaanenburg, R. S. Venema, and M.A. Westenberg, “car license plate recognition with neural networks and fuzzy logic”, Proceedings of IEEE International Conference on Neural Networks, vol.5, pp. 2232-2236, 1995.
[27] H. A. ; R.J. de la Haye, N. A. Khan, “A High Performance License Plate Recognition System”, IEEE International Conference on systems, Man, and Cybernetics, vol.5, pp.4357-4362, 1998.
[28] P. Comelli, P. Ferragina, M. N. Granieri, and F. Stabile, “Optical recognition of Motor Vehicle License Plates”, IEEE Trans. On Vehicular Tech, vol. 44, no.4, November 1995.
[29] 葉怡成, “類神經網路模式應用與實作”, 儒林圖書公司, 2009.
[30] 張錚, “MATLAB 教學範本程式設計與應用”, 圖龍文化事業公司, 2008.
[31] 朱習軍, 隋思漣, 張賓, 劉尊年, “MATLAB 在信號與圖像處理中的應用”, 電子
工業出版社，2009.
[32] 連國珍, “數位影像處理 MATLAB” , 儒林圖書公司, 2009.
[33] 施威銘研究室, “C最新程式語言”, 旗標股份有限公司, 2004.
[34] 施威銘研究室, “C++最新程式語言”, 旗標股份有限公司, 2008.
[35] C. G. Rafael, R. E. Woods, and S. L. Eddins, Digital Image Processing Using MATLAB, 1st Edition.