Optical Character Recognition Using Novel Feature Extraction & Neural Network Classification Techniques

This paper describes two novel techniques applied to the jkature extraction and pattern classification stages in an OCR system for typeset characters. A technique for estimating the class discrimination ability of continuous valued jkatures is presented leading to the formation of complex features which facilitate the classifimtion stage. Next, a neural network ClQSSafieT trained wing a nxently proposed powerfisl training algorithm, based m rigorous nonlinear programming methods, kz applied to large-scale OCR problems involving typeset Greek characters and found to exhibit good generalization capabilities compared to other conventional and artificial neural network (ANN) classifiers. Combining these jkature extraction and classification techniques in a unified software platform, we have designed an OCR system which achieved high mognition rates in some real world OCR ezperiments.

[1]  D. A. Karras,et al.  Pattern classification using a generalised Hamming distance metric , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[2]  Lee A. Feldkamp,et al.  Strategies and issues in applications of neural networks , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[3]  S. J. Perantonis,et al.  Comparison of learning algorithms for feedforward networks in large scale networks and problems , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[4]  Edward H. Adelson,et al.  The Laplacian Pyramid as a Compact Image Code , 1983, IEEE Trans. Commun..

[5]  Petri Koistinen,et al.  Using additive noise in back-propagation training , 1992, IEEE Trans. Neural Networks.

[6]  Dimitris A. Karras,et al.  An efficient constrained learning algorithm with momentum acceleration , 1995, Neural Networks.

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

[8]  David E. Rumelhart,et al.  Generalization by Weight-Elimination with Application to Forecasting , 1990, NIPS.

[9]  P. Burt.  Fast filter transform for image processing , 1981 .

[10]  P. J. Burt,et al.  Fast Filter Transforms for Image Processing , 1981 .

[11]  S. J. Perantonis,et al.  A fast constrained learning algorithm based on the construction of suitable internal representations , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

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

[13]  A. E. Bryson,et al.  A Steepest-Ascent Method for Solving Optimum Programming Problems , 1962 .

[14]  A. Khotanzad,et al.  Distortion invariant character recognition by a multi-layer perceptron and back-propagation learning , 1988, IEEE 1988 International Conference on Neural Networks.

[15]  Dimitris A. Karras,et al.  An efficient constrained training algorithm for feedforward networks , 1995, IEEE Trans. Neural Networks.

[16]  Dimitrios Alexios Karras,et al.  Minimum Distance Pattern Classifiers Based On A New Distance Metric , 1993 .