Evaluating a Zoning Mechanism and Class-Modular Architecture for Handwritten Characters Recognition

In this article we propose a feature extraction procedure based on directional histograms and investigate the application of a nonconventional neural network architecture, applied to the problem of handwritten character recognition. This approach is inspired on some characteristics of the human visual system, as it focus attention on high spatial frequencies and on the recognition of local features. Two architectures were tested and evaluated: a conventional MLP (Multiple Layer Perceptron) and a class-modular MLP. Experiments developed with the Letter database produced a recognition rate of 93.67% for the class-modular MLP. Other set of experiments utilized the IRONOFF database resulting in recognition rates of 89.21% and 80.75% for uppercase and lowercase characters respectively, also with the class-modular MLP.

[1]  Luiz Eduardo Soares de Oliveira,et al.  Handwritten Character Recognition Using Nonsymmetrical Perceptual Zoning , 2007, Int. J. Pattern Recognit. Artif. Intell..

[2]  Catherine Blake,et al.  UCI Repository of machine learning databases , 1998 .

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

[4]  Cinthia Obladen de Almendra Freitas,et al.  Methodology for the design of NN-based month-word recognizers written on Brazilian bank checks , 2007, Image Vis. Comput..

[5]  Jose C. Principe,et al.  Neural and Adaptive Systems: Fundamentals through Simulations with CD-ROM , 1999 .

[6]  Ching Y. Suen,et al.  Analysis and recognition of alphanumeric handprints by parts , 1992, Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol.II. Conference B: Pattern Recognition Methodology and Systems.

[7]  E. Poisson,et al.  Multi-modular architecture based on convolutional neural networks for online handwritten character recognition , 2002, Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02..

[8]  Stefan Knerr,et al.  The IRESTE On/Off (IRONOFF) dual handwriting database , 1999, Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR '99 (Cat. No.PR00318).

[9]  Guoqiang Peter Zhang,et al.  Neural networks for classification: a survey , 2000, IEEE Trans. Syst. Man Cybern. Part C.

[10]  Meng Shi,et al.  Handwritten numeral recognition using gradient and curvature of gray scale image , 2002, Pattern Recognit..

[11]  Ching Y. Suen,et al.  A class-modular feedforward neural network for handwriting recognition , 2002, Pattern Recognit..

[12]  Ryan M. Rifkin,et al.  In Defense of One-Vs-All Classification , 2004, J. Mach. Learn. Res..

[13]  V. Kvasnicka,et al.  Neural and Adaptive Systems: Fundamentals Through Simulations , 2001, IEEE Trans. Neural Networks.