Skip to main content
SpringerLink
Log in

Part-based methods for handwritten digit recognition

  • Research Article
  • Published:
Frontiers of Computer Science Aims and scope Submit manuscript

Abstract

In this paper, we intensively study the behavior of three part-based methods for handwritten digit recognition. The principle of the proposed methods is to represent a handwritten digit image as a set of parts and recognize the image by aggregating the recognition results of individual parts. Since part-based methods do not rely on the global structure of a character, they are expected to be more robust against various deformations which may damage the global structure. The proposed three methods are based on the same principle but different in their details, for example, the way of aggregating the individual results. Thus, those methods have different performances. Experimental results show that even the simplest part-based method can achieve recognition rate as high as 98.42% while the improved one achieved 99.15%, which is comparable or even higher than some state-of-the-art method. This result is important because it reveals that characters can be recognized without their global structure. The results also show that the part-based method has robustness against deformations which usually appear in handwriting.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Bart E, Ullman S. Class-based matching of object parts. In: Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop. 2004, 173

    Chapter  Google Scholar 

  2. Zhang J, MarszaÅĆek M, Lazebnik S, Schmid C. Local features and kernels for classification of texture and object categories: a comprehensive study. International Journal of Computer Vision, 2007, 73(2): 213–238

    Article  Google Scholar 

  3. Mikolajczyk K, Schmid C. A performance evaluation of local descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1615–1630

    Article  Google Scholar 

  4. Plamondon R, Srihari S N. Online and off-line handwriting recognition: a comprehensive survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(1): 63–84

    Article  Google Scholar 

  5. Carneiro G. The automatic design of feature spaces for local image descriptors using an ensemble of non-linear feature extractors. In: Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition. 2010, 3509–3516

    Chapter  Google Scholar 

  6. Lim K L, Galoogahi H K. Shape classification using local and global features. In: Proceedings of the 4th Pacific-Rim Symposium on Image and Video Technology. 2010, 115–120

    Chapter  Google Scholar 

  7. Keren D. Painter identification using local features and naive bayes. In: Proceedings of the 2002 International Conference on Pattern Recognition. 2002, 474–477

    Google Scholar 

  8. Bart E, Byvatov E, Ullman S. View-invariant recognition using corresponding object fragments. Computer Vision, 2004, 152-165

  9. Song C, Yang F, Li P. Rotation invariant texture measured by local binary pattern for remote sensing image classification. In: Proceedings of the 2010 International Workshop on Education Technology and Computer Science. 2010, 3–6

    Chapter  Google Scholar 

  10. Liang P, Li S F, Qin J W. Multi-resolution local binary patterns for image classification. In: Proceedings of the 2010 International Conference onWavelet Analysis and Pattern Recognition. 2010, 164–169

    Chapter  Google Scholar 

  11. Suruliandi A, Srinivasan E M, Ramar K. Image resolution dependency of local texture patterns in classification of color images. In: Proceedings of the 2010 IEEE Annual India Conference. 2010, 1–6

    Chapter  Google Scholar 

  12. Lazebnik S, Schmid C, Ponce J. Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: Proceedings of the 2006 Computer Society Conference on Computer Vision and Pattern Recognition. 2006, 2169–2178

    Google Scholar 

  13. Ullman S, Epshtein B. Visual classification by a hierarchy of extended fragments. In: Proceedings of Toward Category-Level Object Recognition. 2006, 321–344

    Chapter  Google Scholar 

  14. Ohm J R, Ma P. Feature-based cluster segmentation of image sequences. In: Proceedings of the 1997 International Conference on Image Processing. 1997, 178–181

    Google Scholar 

  15. Wakabayashi T, Tsuruoka S, Kimura F, Miyake Y. On the size and variable transformation of feature vector for handwritten character recognition. IEICE Transactions Japan, 1993, J76-D-II(12): 2495–2503

    Google Scholar 

  16. Srikantan G, Lam SW, Srihari S N. Gradient-based contour encoding for character recognition. Pattern Recognition, 1996, 29(7): 1147–1160

    Article  Google Scholar 

  17. Belongie S, Malik J, Puzicha J. Shape matching and object recognition using shape contexts. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(4): 509–522

    Article  Google Scholar 

  18. Lecun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 1998, 86(11): 2278–2324

    Article  Google Scholar 

  19. Teow L N, Loe K F. Robust vision-based features and classification schemes for off-line handwritten digit recognition. Pattern Recognition, 2002, 35(11): 2355–2364

    Article  MATH  Google Scholar 

  20. Mayraz G, Hinton G E. Recognizing handwritten digits using hierarchical products of experts. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(2): 189–197

    Article  Google Scholar 

  21. Liu C L, Nakashima K, Sako H, Fujisawa H. Handwritten digit recognition: benchmarking of state-of-the-art techniques. Pattern Recognition, 2003, 36(10): 2271–2285

    Article  MATH  Google Scholar 

  22. Li Z C, Suen C Y. Crucial combinations of parts for handwritten alphanumeric characters. Mathematical and Computer Modelling, 2000, 31(8-9): 193–229

    Article  MathSciNet  Google Scholar 

  23. Li Z C, Li H J, Suen C Y, Wang H Q, Liao S Y. Recognition of handwritten characters by parts with multiple orientations. Mathematical and Computer Modelling, 2002, 35(3–4): 441–479

    Article  MATH  Google Scholar 

  24. Suen C Y, Guo J, Li Z C. Analysis and recognition of alphanumeric handprints by parts. IEEE Transactions on Systems, Man and Cybernetics, 1994, 24(4): 614–631

    Article  Google Scholar 

  25. Li Z C, Suen C Y. The partition-combination method for recognition of handwritten characters. Pattern Recognition Letters, 2000, 21(8): 701–720

    Article  MathSciNet  MATH  Google Scholar 

  26. Chellapilla K, Simard P. Using machine learning to break visual human interaction proofs (HIPs). Advances in Neural Information Processing Systems, 2004, 17: 265–272

    Google Scholar 

  27. Chellapilla K, Larson K, Simard P, Czerwinski M. Computers beat humans at single character recognition in reading based human interaction proofs. In: Proceedings of the 2005 Conference on Email and Anti-Spam. 2005

    Google Scholar 

  28. Mori G, Malik J. Recognizing objects in adversarial clutter: Breaking a visual CAPTCHA. In: Proceedings of the 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2003, 134–141

    Chapter  Google Scholar 

  29. Campos T E, Babu B R, Varma M. Character recognition in natural images. In: Proceedings of the 2009 International Conference on Computer Vision Theory and Applications. 2009

    Google Scholar 

  30. Coates A, Carpenter B, Case C, Satheesh S, Suresh B, Wang T, Wu D J, Ng A Y. Text detection and character recognition in scene images with unsupervised feature learning. In: Proceedings of the 2011 International Conference on Document Analysis and Recognition. 2011, 440–445

    Chapter  Google Scholar 

  31. Diem M, Sablatnig R. Recognition of degraded handwritten characters using local features. In: Proceedings of the 2009 International Conference on Document Analysis and Recognition. 2009, 221–225

    Chapter  Google Scholar 

  32. Diem M, Sablatnig R. Are characters objects? In: Proceedings of International Conference on Frontiers in Handwriting Recognition. 2010, 565–570

    Google Scholar 

  33. Garz A, Diem M, Sablatnig R. Detecting text areas and decorative elements in ancient manuscripts. In: Proceedings of the 2010 International Conference on Frontiers in Handwriting Recognition. 2010, 176–181

    Chapter  Google Scholar 

  34. Sankar K P, Jawahar C V, Manmatha R. Nearest neighbor based collection ocr. In: Proceedings of the 2010 International Workshop on Document Analysis Systems. 2010, 207–214

    Google Scholar 

  35. Bay H, Tuytelaars T, Van Gool L. Surf: speeded up robust features. Computer Vision, 2006, 404–417

    Google Scholar 

  36. Lowe D G. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 2004, 60(2): 91–110

    Article  Google Scholar 

  37. Boiman O, Shechtman E, Irani M. In defense of nearest-neighbor based image classification. In: Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition. 2008, 1–8

    Chapter  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Intelligent Systems, Graduate School of Information Science and Electrical Engineering, Kyushu University, Fukuoka, 819-0395, Japan

    Song Wang, Seiichi Uchida & Yaokai Feng

  2. German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, D-67663, Germany

    Marcus Liwicki

Authors
  1. Song Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Seiichi Uchida
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Marcus Liwicki
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yaokai Feng
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Song Wang.

Additional information

Song Wang received his BS in physics from Hebei University, and ME in computer science from Huazhong University of Science and Technology, China. Since 2010, he has been a PhD student in the Department of Intelligent Systems of the Graduate School of Information Science and Electrical Engineering, Kyushu University, Japan. His research interests include pattern recognition, off-line and on-line handwritten character recognition, image classification, scene character detection, and document analysis.

Seiichi Uchida received BE, ME, and PhD from Kyushu University, Japan, in 1990, 1992, and 1999, respectively. From 1992 to 1996, he joined SECOM Co., Ltd., Japan. Currently, he is a professor at Kyushu University. His research interests include pattern recognition and image processing. He received 2002 IEICE PRMU Research Encouraging Award, 2008 IEICE Best Paper Award, MIRU 2006 Nagao Award (best paper award), MIRU 2011 Excellent Paper Award, 2007 IAPR/ICDAR Best Paper Award, and 2010 ICFHR Best Paper Award. Dr. Uchida is a member of IEEE and IPSJ.

Marcus Liwicki received his MS in computer science from the Free University of Berlin, Germany, in 2004, and his PhD from the University of Bern, Switzerland, in 2007. Subsequently, he received the postdoctoral lecture qualification from the Technical University of Kaiserslautern, Germany, in 2011. Currently he is a senior researcher and private lecturer at the German Research Center for Artificial Intelligence (DFKI). His research interests include knowledge management, semantic desktop, electronic pen-input devices, on-line and off-line handwriting recognition, and document analysis. From October 2009 to March 2010 he visited Kyushu University (Fukuoka, Japan) as a research fellow, supported by the Japanese Society for the Promotion of Science.

Yaokai Feng received his BE andME in computer science from Tianjin University, China, in 1986 and 1992, respectively. He received his PhD in information science from Kyushu University, Japan, in 2004. Now, he is an assistant professor at Kyushu University, Japan. His current research interests include database, pattern recognition, information retrieval, and network security. In 2011, he received MIRU 2011 Excellent Paper Award. He is a member of IPSJ and IEEE.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Wang, S., Uchida, S., Liwicki, M. et al. Part-based methods for handwritten digit recognition. Front. Comput. Sci. 7, 514–525 (2013). https://doi.org/10.1007/s11704-013-2297-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11704-013-2297-x

Keywords

Search

Navigation