請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/52038完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 黃乾綱 | |
| dc.contributor.author | Shih-Han Wang | en |
| dc.contributor.author | 王詩涵 | zh_TW |
| dc.date.accessioned | 2021-06-15T14:04:38Z | - |
| dc.date.available | 2017-12-01 | |
| dc.date.copyright | 2015-12-01 | |
| dc.date.issued | 2015 | |
| dc.date.submitted | 2015-08-20 | |
| dc.identifier.citation | 1. Abbey Finereader. Available from: http://www.abbyy.com/finereader/.
2. 丹青文件辨識系統. Available from: http://www.newsoft.com.tw/. 3. Plustek. Available from: http://plustek.com/tc/. 4. tesseract-ocr. Available from: https://code.google.com/p/tesseract-ocr/. 5. Shiah, C.-Y. and Y.-S. Yen. Fast historic document retrieval by extracting document image summary. in Multimedia Technology (ICMT), 2011 International Conference on. 2011. IEEE. 6. Bieniecki, W., S. Grabowski, and W. Rozenberg. Image preprocessing for improving ocr accuracy. in Perspective Technologies and Methods in MEMS Design, 2007. MEMSTECH 2007. International Conference on. 2007. IEEE. 7. Ji, J., L. Peng, and B. Li. Graph Model Optimization Based Historical Chinese Character Segmentation Method. in Document Analysis Systems (DAS), 2014 11th IAPR International Workshop on. 2014. IEEE. 8. Xu, L., et al., An over-segmentation method for single-touching Chinese handwriting with learning-based filtering. International Journal on Document Analysis and Recognition (IJDAR), 2014. 17(1): p. 91-104. 9. Zhao, S., et al., Two-stage segmentation of unconstrained handwritten Chinese characters. Pattern Recognition, 2003. 36(1): p. 145-156. 10. Yang, L. and L. Peng. Local projection-based character segmentation method for historical Chinese documents. in IS&T/SPIE Electronic Imaging. 2013. International Society for Optics and Photonics. 11. Devi, H., Thresholding: A Pixel-Level image processing methodology preprocessing technique for an OCR system for the Brahmi script. Ancient Asia, 2011. 1. 12. Dey, P. and S. Noushath, e-PCP: A robust skew detection method for scanned document images. Pattern Recognition, 2010. 43(3): p. 937-948. 13. Luan, D., C. Liu, and X. Ding. General Chinese document capture system with improved error-rejecting module. in Electronic Imaging 2003. 2003. International Society for Optics and Photonics. 14. Li, N., et al., Applications of Recurrent Neural Network Language Model in Offline Handwriting Recognition and Word Spotting. 2014, ICFHR. 15. Zhuang, L., et al. A Chinese OCR spelling check approach based on statistical language models. in Systems, Man and Cybernetics, 2004 IEEE International Conference on. 2004. IEEE. 16. Taghva, K., S. Poudel, and S. Malreddy. Post processing with first-and second-order hidden Markov models. in IS&T/SPIE Electronic Imaging. 2013. International Society for Optics and Photonics. 17. Lu, Y. and C.L. Tan, Chinese word searching in imaged documents. International Journal of Pattern Recognition and Artificial Intelligence, 2004. 18(02): p. 229-246. 18. Tong, X. and D.A. Evans. A statistical approach to automatic OCR error correction in context. in Proceedings of the fourth workshop on very large corpora. 1996. 19. Wick, M.L., M.G. Ross, and E.G. Learned-Miller. Context-sensitive error correction: Using topic models to improve OCR. in Document Analysis and Recognition, 2007. ICDAR 2007. Ninth International Conference on. 2007. IEEE. 20. Bassil, Y. and M. Alwani, Ocr post-processing error correction algorithm using google online spelling suggestion. arXiv preprint arXiv:1204.0191, 2012. 21. 周嘉彬, 應用詞彙, 語法與語料規則於中文手寫句辨識之校正模組. 2010. 22. Cao, Z., et al. Face recognition with learning-based descriptor. in Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on. 2010. IEEE. 23. Lu, W.-m., et al., Efficient shape matching for Chinese calligraphic character retrieval. Journal of Zhejiang University SCIENCE C, 2011. 12(11): p. 873-884. 24. 周纬, 陈良育, and 曾振柄, 基于几何形状分析的藏文字符识别. Computer Engineering and Applications, 2012. 48(18). 25. 江萍, 徐晓冰, and 方敏, 基于形态学骨架提取算法的研究及其实现. 计算机应用, 2003(z1): p. 136-137. 26. Bishop, C.M., Pattern recognition and machine learning. 2006: springer. 27. Jang, J.-S.R., Data Clustering and Pattern Recognition. 28. Lloyd, S.P., Least squares quantization in PCM. Information Theory, IEEE Transactions on, 1982. 28(2): p. 129-137. 29. Takeuchi, K. and Y. Matsumoto, Japanese OCR error correction using stochastic morphological analyzer and probabilistic word N-gram model. International Journal of Computer Processing of Oriental Languages, 2000. 13(01): p. 69-82. 30. 曾元顯, 應用於資訊檢索的中文 OCR 錯誤詞彙自動更正. 中國圖書館學 [3] 會會報, 2004(72): p. 23-31. 31. Lee, C.-m. and C.-K. Huang, Context-Based Chinese Word Segmentation using SVM Machine-Learning Algorithm without Dictionary Support. 32. Rand, W.M., Objective criteria for the evaluation of clustering methods. Journal of the American Statistical association, 1971. 66(336): p. 846-850. 33. Rosenberg, A. and J. Hirschberg. V-Measure: A Conditional Entropy-Based External Cluster Evaluation Measure. in EMNLP-CoNLL. 2007. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/52038 | - |
| dc.description.abstract | 隨著時代演進，人們對於電子產品的使用已逐漸普及。傳達文字訊息的方式，由過去的書寫文字，進而進展成現在的數位文字。促使文本數位化的需求提升。為了使影像轉換為數位文字，市面上已有開發光學文字辨識系統，能將影像做自動轉換數位文字，但是這些系統主要是針對現代印刷字體。至於非印刷體文字，如手寫字、雕版印刷等，其辨識率並不佳。因此，本研究，為了改善現有光學文字辨識軟體正確率，增加使用者數位化文本的便利性以減少使用之人力成本。
本研究流程主要分為二步驟，第一步驟：將文本作結構的分析，切割出字符影像，避免切割不完全使得辨識時造成辨識錯誤。第二步驟分為兩個部分，第一部分是將切割出的字符，以方向梯度直方圖(HOG)來表示字符特徵。將字符依特徵向量作粗略分群，再以文本之語言模型，觀察其分群情況，增加其分群效果。最後根據分群的結果，作錯誤辨識的偵測，以及改正其錯誤文字；第二部分是將文本利用現有之文字辨識軟體，將影像轉為數位文字，透過外部文本的語言模型來偵測與改正錯誤文字。最後比較這兩部分之錯誤字偵測及修正情形。本研究方法與使用Plustek DI express 6.0辨識的結果作比較，在使用內部文本的部分，增加5%的辨識正確率，從65%增加至70%。而使用外部文本的部分，則是增加了9.8%的辨識正確率。 | zh_TW |
| dc.description.provenance | Made available in DSpace on 2021-06-15T14:04:38Z (GMT). No. of bitstreams: 1 ntu-104-R02525063-1.pdf: 2155429 bytes, checksum: 79829e95c513bf6ba6c7517561b423b8 (MD5) Previous issue date: 2015 | en |
| dc.description.tableofcontents | 誌謝 i
摘要 ii ABSTRACT iii 目錄 iv 圖目錄 vii 表目錄 ix Chapter 1 緒論 1 1.1 研究背景與動機 1 1.2 研究目的 3 1.3 研究貢獻 4 1.4 論文架構 4 Chapter 2 文獻探討 5 2.1 光學字符辨識(OCR) 5 2.2 光學字符辨識正確率提升 5 2.2.1 前處理 6 2.2.2 後處理 7 2.3 特徵擷取 8 2.3.1 方向梯度直方圖(HOG) 8 2.3.2 字符骨架特徵 10 2.4 統計型語言模型 11 2.5 非監督式學習 12 Chapter 3 研究方法 15 3.1 研究方法架構 15 3.2 字符影像擷取 17 3.2.1 區塊及行切割 18 3.2.2 字符切割 19 3.3 字符影像辨識 21 3.3.1 特徵擷取 22 3.3.2 字符分群 23 3.3.3 透過語言模型改善分群結果 24 3.4 OCR後處理 26 3.4.1 外部文本錯誤字偵測與更正 26 3.4.2 利用內部文本錯誤字偵測與更正 28 Chapter 4 實驗結果與討論 29 4.1 實驗資料 29 4.1.1 實驗文本 29 4.1.2 光學字符辨識系統 31 4.1.3 外部文本 31 4.2 字符切割 31 4.3 分群結果 33 4.3.1 分群效果評估方法介紹 33 4.4 OCR錯誤偵測與改正 36 Chapter 5 結論與未來展望 37 參考文獻 39 附錄 43 | |
| dc.language.iso | zh-TW | |
| dc.subject | 光學字符辨識 | zh_TW |
| dc.subject | 漢字辨識 | zh_TW |
| dc.subject | 語言模型 | zh_TW |
| dc.subject | Language model | en |
| dc.subject | Chinese character recognition | en |
| dc.subject | Optical Character Recognition | en |
| dc.title | 基於文本的漢字影像辨識研究 | zh_TW |
| dc.title | Language Context-based Enhancement for Chinese Optical Character Recognition | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 103-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 傅楸善,張恆華 | |
| dc.subject.keyword | 漢字辨識,語言模型,光學字符辨識, | zh_TW |
| dc.subject.keyword | Chinese character recognition,Language model,Optical Character Recognition, | en |
| dc.relation.page | 46 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2015-08-20 | |
| dc.contributor.author-college | 工學院 | zh_TW |
| dc.contributor.author-dept | 工程科學及海洋工程學研究所 | zh_TW |
| 顯示於系所單位： | 工程科學及海洋工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-104-1.pdf 未授權公開取用 | 2.1 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。