Handwritten Character Recognition using Perceptual Fuzzy-Zoning and Class Modular Neural Networks

This paper present a novel feature extraction method for offline recognition of segmented handwritten characters based on the fuzzy-zoning and normalized vector distance measures. Experiments are conducted on forty four basic Malayalam handwritten characters. In the recognition experiments are conducted using class modular neural network with the proposed features and this method is found to be promising.

[1]  Kishan G. Mehrotra,et al.  Efficient classification for multiclass problems using modular neural networks , 1995, IEEE Trans. Neural Networks.

[2]  M. Lévesque.  Perception , 1986, The Yale Journal of Biology and Medicine.

[3]  E. Backer,et al.  A structural approach of pattern recognition , 1980 .

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

[5]  Anil K. Jain,et al.  Statistical Pattern Recognition: A Review , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Lambertus Schomaker.  A method for the determination of features used in human reading of cursive handwriting. , 1998 .

[7]  Rabab Kreidieh Ward,et al.  A Rotation Invariant Rule-Based Thinning Algorithm for Character Recognition , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

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

[9]  Patrick Shen-Pei Wang,et al.  An Adaptive Modular Neural Network with Application to Unconstrained Character Recognition , 1994, Int. J. Pattern Recognit. Artif. Intell..

[10]  Mindy Bokser,et al.  Omnidocument technologies , 1992, Proc. IEEE.

[11]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[12]  Cinthia Obladen de Almendra Freitas,et al.  Evaluating the conventional and class-modular architectures feedforward neural network for handwritten word recognition , 2003, 16th Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI 2003).