Orientational features with the SNT-grid

The Scanning N-Tuple Grid (SNT-Grid) has been demonstrated to be a fast classifier for 2-dimensional images. The high speed is accomplished by scanning separately along rows and columns to extract features and can process thousands of pre-segmented characters per second in training and recognition. This paper proposes the use of orientational features within the SNT-Grid and makes a comparison in performance with features previously reported in literature. In terms of training the classifier, it explores cross entropy training and concludes that it outperforms more conventional maximum likelihood training. Finally, zoned orientational features offer a better implementation with an additional cost in computational time for training and recognition. The best accuracy reported has reduced the error rate of the system by 70% on the same dataset.

[1]  Colin Giles,et al.  Learning, invariance, and generalization in high-order neural networks. , 1987, Applied optics.

[2]  Simon M. Lucas.  High performance OCR with syntactic neural networks , 1995 .

[3]  George Tambouratzis.  Improving the Clustering Performance of the Scanning n-Tuple Method by Using Self-Supervised Algorithms to Introduce Subclasses , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Orly Yadid-Pecht,et al.  Modified high-order neural network for invariant pattern recognition , 2005, Pattern Recognit. Lett..

[5]  Michael C. Fairhurst,et al.  Bit plane decomposition and the scanning n-tuple classifier , 2002, Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition.

[6]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[7]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[8]  Simon M. Lucas,et al.  Sequence recognition with scanning N-tuple ensembles , 2004, ICPR 2004.

[9]  Simon M. Lucas,et al.  Statistical syntactic methods for high-performance OCR , 1996 .

[10]  Michael C. Fairhurst,et al.  A new chain-code quantization approach enabling high performance handwriting recognition based on multi-classi .er schemes , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[11]  Herbert Freeman,et al.  Computer Processing of Line-Drawing Images , 1974, CSUR.

[12]  Simon M. Lucas.  Discriminative Training of the Scanning N-Tuple Classifier , 2003, IWANN.

[13]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[14]  Simon M. Lucas,et al.  Fast convolutional OCR with the scanning N-tuple grid , 2005, Eighth International Conference on Document Analysis and Recognition (ICDAR'05).

[15]  Anil K. Jain,et al.  Feature extraction methods for character recognition-A survey , 1996, Pattern Recognit..