A Hybrid Scheme for Handprinted Numeral Recognition Based on a Self-Organizing Network and MLP Classifiers

This paper proposes a novel approach to automatic recognition of handprinted Bangla (an Indian script) numerals. A modified Topology Adaptive Self-Organizing Neural Network is proposed to extract a vector skeleton from a binary numeral image. Simple heuristics are considered to prune artifacts, if any, in such a skeletal shape. Certain topological and structural features like loops, junctions, positions of terminal nodes, etc. are used along with a hierarchical tree classifier to classify handwritten numerals into smaller subgroups. Multilayer perceptron (MLP) networks are then employed to uniquely classify the numerals belonging to each subgroup. The system is trained using a sample data set of 1800 numerals and we have obtained 93.26% correct recognition rate and 1.71% rejection on a separate test set of another 7760 samples. In addition, a validation set consisting of 1440 samples has been used to determine the termination of the training algorithm of the MLP networks. The proposed scheme is sufficiently robust with respect to considerable object noise.

[1]  Sargur N. Srihari,et al.  Recognition of handwritten and machine-printed text for postal address interpretation , 1993, Pattern Recognit. Lett..

[2]  Bidyut Baran Chaudhuri,et al.  Skeletonization by a topology-adaptive self-organizing neural network , 2001, Pattern Recognit..

[3]  Bidyut Baran Chaudhuri,et al.  A complete printed Bangla OCR system , 1998, Pattern Recognit..

[4]  Bernd Fritzke,et al.  Growing cell structures--A self-organizing network for unsupervised and supervised learning , 1994, Neural Networks.

[5]  Sang-Hui Park,et al.  Self-creating and organizing neural networks , 1994, IEEE Trans. Neural Networks.

[6]  Masafumi Hagiwara,et al.  A simple and effective method for removal of hidden units and weights , 1994, Neurocomputing.

[7]  Ujjwal Bhattacharya,et al.  Self-adaptive learning rates in backpropagation algorithm improve its function approximation performance , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[8]  Amar Mitiche,et al.  Modeling and classification of shape using a Kohonen associative memory with selective multiresolution , 1993, Neural Networks.

[9]  Fumitaka Kimura,et al.  Handwritten numerical recognition based on multiple algorithms , 1991, Pattern Recognit..

[10]  Sargur N. Srihari,et al.  On-Line and Off-Line Handwriting Recognition: A Comprehensive Survey , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Adnan Amin,et al.  Off-line Arabic character recognition: the state of the art , 1998, Pattern Recognit..

[12]  Majid Ahmadi,et al.  Recognition of handwritten numerals with multiple feature and multistage classifier , 1995, Pattern Recognit..

[13]  Ching Y. Suen,et al.  Computer recognition of unconstrained handwritten numerals , 1992, Proc. IEEE.

[14]  Ching Y. Suen,et al.  Historical review of OCR research and development , 1992, Proc. IEEE.

[15]  Michael D. Garris,et al.  Neural network-based systems for handprint OCR applications , 1998, IEEE Trans. Image Process..

[16]  Thomas Martinetz,et al.  'Neural-gas' network for vector quantization and its application to time-series prediction , 1993, IEEE Trans. Neural Networks.

[17]  Thomas Martinetz,et al.  Topology representing networks , 1994, Neural Networks.