Please use this identifier to cite or link to this item:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/47867
Full metadata record
???org.dspace.app.webui.jsptag.ItemTag.dcfield??? | Value | Language |
---|---|---|
dc.contributor.advisor | 陳銘憲 | |
dc.contributor.author | I-Chun Chen | en |
dc.contributor.author | 陳怡君 | zh_TW |
dc.date.accessioned | 2021-06-15T06:23:24Z | - |
dc.date.available | 2015-08-10 | |
dc.date.copyright | 2010-08-10 | |
dc.date.issued | 2010 | |
dc.date.submitted | 2010-08-09 | |
dc.identifier.citation | [1] R. Dai, C. Liu, and B. Xiao, “Chinese character recognition: history, status and prospects,” Frontiers of Computer Science in China, pp. 126–136, 2007.
[2] K. Ding, Z.B. Liu, L.W. Jin, and X.H Zhu, “A Comparative Study of Gabor Feature and Gradient Feature for Handwritten Chinese Character Recognition,” International Conference on Wavelet Analysis and Pattern Recognition, 2007. [3] N. Ezaki, M. Bulacu and L. Schomaker, “Text Detection from Natural Scene Images; Towards a System for Visually Impaired Persons,” International Conference on Pattern Recognition, pp. 683-686, 2004. [4] J. Gao and J. Yang, “An Adaptive Algorithm for Text Detection from Natural Scenes,' Proc. of Computer Vision and Pattern Recognition (CVPR), 2001. [5] B. Gatos, I. Pratikakis, K. Kepene, S.J. Perantonis, “Text detection in indoor/outdoor scene images,” Proc. First Workshop of Camera-based Document Analysis and Recognition, pp. 127–132, 2005. [6] V.K. Govindan and A.P. Shivaprasad, “Character recognition- A review,” Pattern Recognition vol.23, no.7, pp.671-683, 1990. [7] C.C. Han, Y.L. Tseng, K.C. Fan and A.B. Wang, “Coarse classification of Chinese characters via stroke clustering method,” Pattern Recognition Letters, 1995. [8] A.K. Jain, and Y. Zhong, “Page Segmentation using Texture Analysis,” Pattern Recognition, pp. 743-770, 1996. [9] K. Jung, K. I. Kim, and A. K. Jain, “Text information extraction in images and video: a survey,” Pattern Recognition, vol. 37, no. 5, pp. 977-997, 2004. [10] F. Kimura, T. Wakabayashi, S. Tsuruoka, and Y. Miyake, “Improvement of handwritten Japanese character recognition using weighted direction code histogram,” Pattern Recognition, 30(8): 1329-1337, 1997. [11] C.J. Lin, C.C. Liu, and H.H. Chen, “A simple method for Chinese video OCR and its application to question answering,” Computational Linguistics and Chinese Language Processing, vol. 6, no. 2, pp. 11–30, 2001. [12] H. Nakajima, Y. Matsuo, M. Nagata, and K. Saito, “Portable Translator Capable of Recognizing Characters on Signboard and Menu Captured by Built-in Camera,” ACL Interactive Poster and Demonstration Sessions, 2005. [13] R.I. Oka, “Handwritten Chinese-Japanese Characters Recognition by Using Cellular Feature,” Proceedings 6th International Joint Conference on Pattern Recognition, pp. 783-785, 1982. [14] N. Otsu, 'A Threshold Selection Method from Gray-Level Histograms,' IEEE Transactions on Systems, Man, and Cybernetics, Vol. 9, No. 1, pp. 62-66, 1979. [15] J.H. Park, G.S. Lee, A.N. Lai, E.C. Kim, J.S. Lim, S.H. Kim, H.J. Yang, and S.W. Oh, “Automatic Detection and Recognition of Shop Name in Outdoor Signboard Images,” IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), 2008. [16] S.N. Srihari, X. Yang, and G.R. Ball, “Offline Chinese handwriting recognition: an assessment of current technology,” Frontiers of Computer Science in China, 2007. [17] Y.M. Su and J.F. Wang. “A novel stroke extraction method for Chinese characters using Gabor filters,” Pattern Recognition, 2003. [18] S.S. Tsai, D. Chen, J.P. Singh, and B. Girod, “Rate-effcient, real-time cd cover recognition on a camera-phone,” Proc. of the 16th ACM international conference on Multimedia, 2008. [19] A. Viterbi. “A personal history of the viterbi algorithm,” IEEE Signal Processing Magazine, 2006. [20] X.W. Wang, X.Q. Ding, and C.S. Liu, “Gabor Filters-based Feature Extraction for Character Recognition,” Pattern Recognition, 2005. [21] K. Wang and J.A. Kangas, “Character Location in Scene Images from Digital Camera,” Pattern Recognition, 2003. [22] T.L. Wu and S.P. Ma, “Feature Extraction By Hierarchical Overlapped Elastic Meshing For Handwritten Chinese Character Recognition,” International Conference on Document Analysis and Recognition (ICDAR), 2003. [23] L. Xu, A. Krzyzak, and C. Y. Suen, “Methods of combining multiple classifiers and their applications to handwriting recognition,” IEEE Trans. System, Man, and Cybernetics, 27(3): 418-435, 1992. [24] T. Yamaguchi and M. Maruyama, “Character extraction from natural scene images by hierarchical classifiers,” Proc. of International Conference on Pattern Recognition, 2004. [25] Q.X. Ye, J.B. Jiao, J. Huang and H. Yu, “Test detection and restoration in natural scene images,” Journal of Visual Communication and Image Representation, 2007. [26] J. Zhang, X. Chen, J. Yang, and A. Waibel, “A PDA-based Sign Translator,” International Conference on Multimodal Interfaces, 2002. [27] Z. Zhang, L. Jin, K. Ding, and X. Gao, “Character-SIFT: A Novel Feature for Offline Handwritten Chinese Character Recognition,” International Conference on Document Analysis and Recognition (ICDAR), 2009. [28] Adobe Developer Support, Glyph Bitmap Distribution Format (BDF) Specification Version 2.2, 1993. [29] Google Goggles. http://www.google.com/mobile/goggles [30] National Languages Committee of Taiwan. http://140.111.34.54/MANDR/ [31] Srilm official website. http://www.speech.sri.com/projects/srilm/ [32] Snap Tell. http://www.snaptell.com | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/47867 | - |
dc.description.abstract | 近年來由於智慧型手機和無線通訊技術的普及,以及智慧型手機附加了解析度良好的拍照功能及螢幕觸控功能,許多有趣的應用也因此而產生,像是QR code的解碼應用、旅遊地點推薦與標註、商標辨識等功能,皆大幅提升人類生活的便利性。雖然智慧型手機提供了許多實用的功能,但以外國人來台灣旅遊為例,不懂中文或其拼音方法,極有可能會遇到在手持裝置上查詢不便的問題。即使非外國人,對一般人來說,在手機上輸入文字本身就不是一件方便的事情。基於這個想法,本論文提出一個建立於行動裝置上的文字辨識及翻譯服務系統-EzTran,使用者只要使用手機拍照功能搭配本系統的使用者介面來拍攝有興趣的中文文字,便可辨識文字並得到英文翻譯結果及其相關資訊。
EzTran系統期望讓身於戶外的使用者、不方便在手持裝置上打字輸入的老人家和看不懂中文的外國人藉由人性化的使用者介面,打破文字輸入之不便及語言隔閡,能夠很便利地獲得文字翻譯結果與其相關情報。另外,我們以「以辨識招牌為輔助的食物推薦系統」為例,展示EzTran可與其他系統整合,利用其文字辨識來改善人機互動的友善度。 實驗結果顯示,EzTran是一個擁有不錯的辨識率的即時性系統,並且可做為與其他應用完善整合的人機介面前端技術。 | zh_TW |
dc.description.abstract | As the popularity of smart phone and wireless technologies, people are getting used to search for information from the Internet anytime and everywhere. In addition, since the resolution of embedded cameras on mobile devices becomes higher and most smart phones are equipped with the touch screen, a large number of interesting and useful applications have been proposed to improve human life. It is observed that although the translation function can be commonly seen on mobile phones, it is very difficult for foreigners to type Chinese characters for searching. Moreover, for native users, it is still time-consuming and inconvenient to type Chinese characters on portable devices. To solve these problems, we propose a Chinese character recognition and translation service system, EzTran, which is a practical system that provides users to get the translated result in English and the related web pages searched from Google search engine easily by only snapping the text photo.
Moreover, EzTran can also be integrated with other applications. In this thesis, we demonstrate the implementation of a food recommendation system with a shop sign recognition scheme. Extensive experiments have been conducted to verify the effectiveness of the proposed system. Experimental results show that EzTran can generate translation outputs in real time with satisfactory recognition accuracy. | en |
dc.description.provenance | Made available in DSpace on 2021-06-15T06:23:24Z (GMT). No. of bitstreams: 1 ntu-99-R97921025-1.pdf: 1543260 bytes, checksum: dc2a056cacaf76bb4b4cefa84b12ad87 (MD5) Previous issue date: 2010 | en |
dc.description.tableofcontents | 口試委員會審定書 ........................................................................................................... #
Acknowledgements ............................................................................................................i 中文摘要 .......................................................................................................................... ii ABSTRACT .................................................................................................................... iii CONTENTS .....................................................................................................................iv LIST OF FIGURES ..........................................................................................................vi LIST OF TABLES ......................................................................................................... viii Chapter 1 Introduction……………………………………………………………..1 Chapter 2 Related Works....………………………………………………………..4 2.1 Text Extraction ................................................................................................ 4 2.2 Optical Character Recognition and Chinese Character Recognition .............. 5 Chapter 3 System Architecture of EzTran………………………………………...8 3.1 Server End ...................................................................................................... 9 3.2 Client End ..................................................................................................... 10 3.3 Training Database Preparation ...................................................................... 11 3.3.1 Feature Extraction ............................................................................... 12 3.3.2 Linear Discriminant Analysis .............................................................. 12 3.3.3 Minimum Distance Classifier ............................................................. 13 Chapter 4 The Detailed Implementation of EzTran……………………………14 4.1 Image Pre-processing.................................................................................... 15 4.1.1 Otsu’s Method and Hue-based Unbalanced Lighting Processing ....... 15 4.1.2 Histogram-based Character Segmentation .......................................... 19 4.2 Character Recognition .................................................................................. 21 4.2.1 Hierarchical Elastic Meshing .............................................................. 21 4.2.2 Gabor Filters-based Feature Extraction .............................................. 24 4.3 Post-processing: Language Model ................................................................ 26 4.4 Google Translate and Translated Output ...................................................... 27 Chapter 5 Experiment Results and an Extended Application…………………28 5.1 Experimental Results .................................................................................... 28 5.1.1 Discussion of the Image Pre-processing Stage ................................... 28 5.1.2 Dimension Selection of LDA .............................................................. 31 5.1.3 Accuracy Evaluation and Performance Comparison .......................... 33 5.1.4 Comparison with Modern Product ...................................................... 37 5.2 An Extended Application: Shop Sign Recognition Assisted Food Recommendation System ............................................................................. 38 Chapter 6 Conclusion and Future Work…………………………………………40 REFERENCE .................................................................................................................. 42 | |
dc.language.iso | en | |
dc.title | EzTran: 應用於行動裝置上的中文辨識及翻譯服務系統 | zh_TW |
dc.title | EzTran: A Mobile-based Chinese Character Recognition and Translation Service System | en |
dc.type | Thesis | |
dc.date.schoolyear | 98-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 魏宏宇,葉彌妍,楊得年,呂俊賢 | |
dc.subject.keyword | 樣式辨認,行動裝置系統,中文文字辨識,電腦視覺, | zh_TW |
dc.subject.keyword | pattern recognition,mobile-based system,Chinese character recognition,computer vision, | en |
dc.relation.page | 45 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2010-08-09 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 電機工程學研究所 | zh_TW |
Appears in Collections: | 電機工程學系 |
Files in This Item:
File | Size | Format | |
---|---|---|---|
ntu-99-1.pdf Restricted Access | 1.51 MB | Adobe PDF |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.