Recognition of Multi-Stroke Based Online Handwritten Gurmukhi Aksharas

详细信息    查看全文

• 作者：Ravinder Kumar (1)
  Rajendra Kumar Sharma (2)
  Anuj Sharma (3)
  
  1. Department of Computer Science & Engineering ; Thapar University ; Patiala ; India
  2. School of Mathematics and Computer Applications ; Thapar University ; Patiala ; India
  3. Department of Mathematics ; Panjab University ; Chandigarh ; India
  
• 关键词：Gurmukhi ; Feature extraction ; Online handwritten character recognition ; Major stroke ; Minor stroke ; Support Vector Machine
• 刊名：Proceedings of the National Academy of Sciences, India Section A: Physical Sciences
• 出版年：2015
• 出版时间：March 2015
• 年：2015
• 卷：85
• 期：1
• 页码：159-168
• 全文大小：1,655 KB
• 参考文献：1. Jain, AK, Duin, RPW, Jianchang, M (2000) Statistical pattern recognition: a review. IEEE Trans Pattern Anal Mach Intell 22: pp. 4-37 CrossRef
  2. Plamondon, R, Srihari, SN (2000) On-line and off-line handwritten character recognition: a comprehensive survey. IEEE Trans Pattern Anal Mach Intell 22: pp. 63-84 CrossRef
  3. Arica, N, Yarman-Vural, FT (2001) An overview of character recognition focused on off-line handwriting. IEEE Trans Syst Man Cybern Part C Appl Rev 31: pp. 216-233 CrossRef
  4. Lorigo, LM, Govindaraju, V (2006) Offline Arabic handwriting recognition: a survey. IEEE Trans Pattern Anal Mach Intell 28: pp. 712-724 CrossRef
  5. Nagy G (1998) Chinese character recognition: a twenty five year retrospective. Int Conf Pattern Recognit: 163鈥?67
  6. Prasad JR, Kulkarni UV (2014) Gujrati character recognition using adaptive neuro fuzzy classifier. Int Conf Electron Syst Signal Process Comput Tech: 402鈥?07
  7. Sazal MMR, Biswas SK, Amin MF, Murase K (2014) Bangla handwritten character recognition using deep belief network. Int Conf Electr Info Commun Tech: 1鈥?
  8. Manikandan BJ, Shankar G, Anoop V, Datta A, Chakravarthy VS (2002) LEKHAK: a system for online recognition of handwritten Tamil characters. Int Conf Nat Lang Process: 29鈥?6
  9. Sharma A, Kumar R, Sharma RK (2009) Rearrangement of recognized strokes in online handwritten / Gurmukhi word recognition. 10th Int Conf Doc Anal Recognit: 1241鈥?245
  10. Arora, Sandhya (2010) Performance comparison of SVM and ANN for handwritten Devanagari character recognition. IJCSI Int J Comput Sci Issues 7: pp. 18-26
  11. Jawahar CV, Kumar P, Kiran MNSSK, Ravi SS (2003) A Bilingual OCR for Hindi-Telugu documents and its applications. Seventh Int Conf Doc Anal Recognit: 408鈥?12
  12. Pal U, Tetsushi SC, Wakabayashi, Kimura F (2008) Accuracy improvement of Devanagari character recognition combining SVM and MQDF. 11th Int Conf Front Handwrit Recognit: 367鈥?72
  13. Kumar R, Sharma RK (2013) An efficient post processing algorithm for online handwriting / Gurmukhi character recognition using set theory. Int J Pattern Recognit Artif Intell 7(4): 1353002-1-17
  14. Madhvanath, S, Kim, G, Govindaraju, V (1999) Chaincode contour processing for handwritten word recognition. IEEE Trans Pattern Anal Mach Intell 21: pp. 928-932 CrossRef
  15. Slavik, P, Govindaraju, V (2001) Equivalence of different methods for slant and skew corrections in word recognition applications. IEEE Trans Pattern Anal Mach Intell 23: pp. 323-326 CrossRef
  16. Vapnik, VN (1999) The nature of statistical learning theory. Springer, Verlag
  17. Christopher, JCB (1998) A tutorial on support vector machines for pattern recognition. Data Min Knowl Disc 2: pp. 121-167 CrossRef
  18. Vapnik, VN (1998) Statistical Learning Theory. John Wiley & Sons, New York
  19. Chang CC, Lin CJ (2011) LIBSVM: a library for support vector machines. ACM Transactions on Intelligent Systems and Technology 2(3): 1鈥?7. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm
  
• 刊物主题：Physics, general; Applied and Technical Physics; Atomic, Molecular, Optical and Plasma Physics; Quantum Physics;
• 出版者：Springer India
• ISSN：2250-1762

文摘

In this paper, we have proposed Support Vector Machine (SVM) based efficient algorithm for Gurmukhi akshara formation/recognition. To train SVM classifier, a specific training data set has been used that forms an initial base to classify it. Experiment results have been obtained by using the software LibSVM where after preprocessing, coordinates were scaled from1 to 9 using the tool of LibSVM. In this experiment, 46,772 words were initially collected. In these words, 2,47,697 strokes were identified and further annotated. We tested the proposed methodology on 4,310 samples of Gurmukhi aksharas collected from different users. Testing results clearly reveal that for different combinations of Gurmukhi strokes and vowel/nasal, a high degree of accuracy has been achieved.