Part-based methods for handwritten digit recognition

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.

Keywords

handwritten digit recognition / local features / part-based method

References

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

[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

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

[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

[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

[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

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

[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

[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

[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

[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

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

[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

[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

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

[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

[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

[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

[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

[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

[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

[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

[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

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

[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

[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

[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

[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

[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

[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

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

[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

[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

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

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

[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

RIGHTS & PERMISSIONS

2014 Higher Education Press and Springer-Verlag Berlin Heidelberg