![]() |
|
以作者查詢圖書館館藏 、以作者查詢臺灣博碩士 、以作者查詢全國書目 、勘誤回報 、線上人數:31 、訪客IP:3.133.148.119
姓名 林婷葦(Ting-Wei Lin) 查詢紙本館藏 畢業系所 資訊工程學系 論文名稱 利用卷積神經網絡進行手寫數學應用題內容之輕量級多語種分類
(Lightweight Classification of Handwritten Math Application Questions Using Convolutional Neural Networks)相關論文 檔案 [Endnote RIS 格式]
[Bibtex 格式]
[相關文章]
[文章引用]
[完整記錄]
[館藏目錄]
至系統瀏覽論文 ( 永不開放)
摘要(中) 隨著數位學習的普及,越來越多的用戶在智能手機或平板電腦上使用智能筆書寫筆記,手寫辨識技術變得越來越重要,且對於母語較多元的國家來說,多語種手寫文本的數量也越來越多。目前許多辨識系統具有很高的準確度。例如: Google, My-Script 等等,他們在處理手寫文本的辨識這方面已經做得非常地足夠,可是若是讓他們辨識多語種的文檔,其效果就不是原先那麼的好。
為了能夠正確識別這些多語種的手寫文檔,語種識別非常重要。基於國中小學的中文數學應用題之答題文本,本文提出了一個使用計算機視覺、卷積神經網絡以及數學結構表示演算法進行輕量級語種識別系統,對中文字區塊和數學式區塊進行分類,以對應強大的辨識引擎,提高數學應用問題中之作答文本內容的準確性。實驗結果表明,增加了語種識別能夠改善辨識系統,提升了手寫文本識別的正確率。摘要(英) With the popularity of digital learning, more and more users are using smart pens to write notes on their smartphones or tablets. Handwriting recognition technology is becoming more and more important, and for multi-language countries, the number of multi-script/multi-language handwritten documents is also increasing.
In order to correctly recognize these multi-script/multi-language handwritten documents, script identification is very important. Based on the answer documents of Chinese mathematical application for elementary and national schools, this paper proposes a lightweight script identification using computer vision, Convolutional Neural Networks (CNN) and Mathematical Expressions (ME) algorithms to classify Chinese characters and mathematical areas. These areas can be mapped to a powerful recognition engine to improve the accuracy of the answer documents of Chinese mathematical application.
The experimental results show that the addition of script identification can improve the recognition system and improve the accuracy of handwritten document recognition.
關鍵字(中) ★ 多語種
★ 語種 識別
★ 手寫辨識
★ 計算機視覺
★ 卷積神經 網絡
★ 數學 結構表示演算法關鍵字(英) ★ Multi-script
★ Multi-language
★ Handwriting Recognition
★ Script Identification,
★ Convolutional Neural Network
★ Computer Vision
★ Mathematical Expressions論文目次 摘要 I
Abstract II
致謝 III
Table of Contents IV
List of Figures VI
List of Tables VIII
1. Introduction 1
1.1 Background 1
1.2 Importance of research 4
1.3 Research purposes 5
2. Related Works 11
3. System Design & Implementation 15
3.1 Pre-Processing 17
3.1.1 Smoothing Strokes 17
3.1.2 Segmentation 17
3.1.2.1 Text Lines Segmentation (TLS) 18
3.1.2.2 Character Segmentation 21
3.1.3 Standardization 23
3.2 Feature Extraction 25
3.2.1 Text 25
3.2.2 Mathematical Structure 26
3.3 Script Identification using traditional feature 27
3.4 Script Identification using CNN 27
3.5 Script Identification using Mathematical structure algorithms 30
3.6 Recognition using My-Script 32
4. Evaluation 33
4.1 Experiment Design 33
4.2 Experiment Results 34
4.3 System display 37
5. Conclusion & Future Work 38
List of Reference 39參考文獻 [1] N. Zheng, Q. You, and G. Meng, “50 years of image processing and pattern recognition in China,” IEEE Intell. Syst., vol. 23, no. 6, pp. 33–41, Nov.–Dec. 2008.
[2] S. Somanchi, D. B. Neill, “Graph structure learning from unlabeled data for early outbreak detection,” IEEE Intell. Syst., vol. 32, no. 2, pp. 80–84, Mar.-Apr. 2017.
[3] A. Graves, M. Liwicki, S. Fernandez, R. Bertolami, H. Bunke, J. Schmidhuber, “A novel connectionist system for unconstrained handwriting recognition,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 31, no. 5, pp. 855–868, May 2009.
[4] K. Ubul, G. Tursun, A. Aysa, D. Impedovo, G. Pirlo, and T. Yibulayin, “Script identification of multi-script documents: A survey,” IEEE Access., vol. 5, pp. 6546–6559, 2017.
[5] A. M. Namboodiri and A. K. Jain, “Online Handwritten Script Recognition,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 26, no. 1, pp. 124–130, Jan. 2004
[6] D. Keysers, T. Deselaers, H. A. Rowley, L. L. Wang, and V. Carbune, “Multi-language online handwriting recognition,” IEEE Trans. attern Anal. Mach. Intell., vol. 39, no. 6, pp. 1180–1194, Jun. 2017.
[7] A. K. Jain and K. Karu, “Page segmentation using texture analysis,” Pattern Recognit., vol. 29, pp. 743–770, 1996.
[8] K. Roy and K. Majumder, “Trilingual script separation of handwritten postal document,” in Proc. 6th Indian Conf. Comput. Vis., Graph. Image Process, 2008, pp. 693–700.
[9] M. Ma, D. W. Park, S. K. Kim, and S. An, “Online recognition of handwritten Korean and English characters,” Journal of Information Processing Systems., vol. 8, no. 4, pp. 653-668, 2012.
[10] T. Makkar, Y. Kumar, A. K. Dubey, Á Rocha, A. Goyal, “Analogizing time complexity of KNN and CNN in recognizing handwritten digits”, 2017 Fourth International Conference on Image Information Processing (ICIIP)., pp. 1-6, Dec 2017.
[11] Tokinori Suzuki, Atsushi Fujii, “ Mathematical Document Categorization with Structure of Mathematical Expressions”, 2017 ACM/IEEE Joint Conference on Digital Libraries (JCDL)
[12] R. Zanibbi, D. Blostein, J.R. Cordy, “ Recognizing mathematical expressions using tree transformation”, IEEE Transactions on Pattern Analysis and Machine Intelligence ( Volume: 24 , Issue: 11 , Nov 2002 )
[13] Ting Zhang, Harold Mouchère, Christian Viard-Gaudin, “ Recognition of online handwritten mathematical expressions”, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) ( Volume: 34 , Issue: 6 , Dec. 2004 )
[14] Debashis Ghosh , Tulika Dube , Adamane Shivaprasad, “ Script Recognition—A Review”, IEEE Transactions on Pattern Analysis and Machine Intelligence ( Volume: 32 , Issue: 12 , Dec. 2010 )
[15] C. Ronse and P.A. Devijver, “ Connected Components in BinaryImages: The Detection Problem. John Wiley & Sons”, 1984
[16] DIGITAL 2019: GLOBAL INTERNET USE ACCELERATES, https://wearesocial.com/blog/2019/01/digital-2019-global-internet-use-accelerates
指導教授 吳曉光(Hsiao-Kuang Wu) 審核日期 2019-7-25 推文 plurk
funp
live
udn
HD
myshare
netvibes
friend
youpush
delicious
baidu
網路書籤 Google bookmarks
del.icio.us
hemidemi
myshare