Neural network-based systems for handprint OCR applications

Over the last five years or so, neural network (NN)-based approaches have been steadily gaining performance and popularity for a wide range of optical character recognition (OCR) problems, from isolated digit recognition to handprint recognition. We present an NN classification scheme based on an enhanced multilayer perceptron (MLP) and describe an end-to-end system for form-based handprint OCR applications designed by the National Institute of Standards and Technology (NIST) Visual Image Processing Group. The enhancements to the MLP are based on (i) neuron activations functions that reduce the occurrences of singular Jacobians; (ii) successive regularization to constrain the volume of the weight space; and (iii) Boltzmann pruning to constrain the dimension of the weight space. Performance characterization studies of NN systems evaluated at the first OCR systems conference and the NIST form-based handprint recognition system are also summarized.

[1]  James D. Keeler,et al.  A Self-Organizing Integrated Segmentation and Recognition Neural Net , 1991, NIPS.

[2]  Kunihiko Fukushima,et al.  Connected character recognition with a neural network , 1993, Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR '93).

[3]  Patrick J. Grother,et al.  The Second Census Optical Character Recognition Systems Conference , 1994 .

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

[5]  L. K. Hansen,et al.  The Error-Reject Tradeoff , 1997 .

[6]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[7]  Isabelle Guyon,et al.  Neural Network Recognizer for Hand-Written Zip Code Digits , 1988, NIPS.

[8]  Charles L. Wilson,et al.  Information Content in Neural Net Optimization , 1994, Connect. Sci..

[9]  J. Hale,et al.  Methods of Bifurcation Theory , 1996 .

[10]  Yann LeCun,et al.  Optimal Brain Damage , 1989, NIPS.

[11]  D. Signorini,et al.  Neural networks , 1995, The Lancet.

[12]  Sargur N. Srihari,et al.  Offline recognition of handwritten cursive words , 1992, Electronic Imaging.

[13]  Charles L. Wilson.  Effectiveness of feature and classifier algorithms in character recognition systems , 1993, Electronic Imaging.

[14]  Giovanni Seni,et al.  Large Vocabulary Recognition of On-Line Handwritten Cursive Words , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Seong-Whan Lee,et al.  Integrated segmentation and recognition of connected handwritten characters with recurrent neural network , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[16]  Michael D Garris,et al.  Teaching Computers to Read Handprinted Paragraphs | NIST , 1996 .

[17]  Ishwar K. Sethi,et al.  Off-line cursive handwriting segmentation , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[18]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[19]  Charles L. Wilson,et al.  Training Dynamics and Neural Network Performance , 1997, Neural Networks.

[20]  Tomaso A. Poggio,et al.  Regularization Theory and Neural Networks Architectures , 1995, Neural Computation.

[21]  James A. Pittman,et al.  Recognizing Hand-Printed Letters and Digits Using Backpropagation Learning , 1991, Neural Computation.

[22]  Maurice Milgram,et al.  Transformation Invariant Autoassociation with Application to Handwritten Character Recognition , 1994, NIPS.

[23]  Keinosuke Fukunaga,et al.  Introduction to statistical pattern recognition (2nd ed.) , 1990 .

[24]  Geoffrey E. Hinton,et al.  To appear in : Advances in Neural Information Processing Systems , 2007 .

[25]  P. Holmes,et al.  Nonlinear Oscillations, Dynamical Systems, and Bifurcations of Vector Fields , 1983, Applied Mathematical Sciences.

[26]  Patrick J. Grother,et al.  Cross-validation comparison of NIST OCR databases , 1993, Electronic Imaging.

[27]  Michael D. Garris,et al.  Analysis of a biologically motivated neural network for character recognition , 1991, ANNA '91.

[28]  Michael D. Garris.  Intelligent form removal with character stroke preservation , 1996, Electronic Imaging.

[29]  Rama Chellappa,et al.  Evaluation of pattern classifiers for fingerprint and OCR applications , 1994, Pattern Recognit..

[30]  S. Ullman.  The Interpretation of Visual Motion , 1979 .

[31]  Alexander Shustorovich,et al.  A subspace projection approach to feature extraction: The two-dimensional gabor transform for character recognition , 1994, Neural Networks.

[32]  Isabelle Guyon,et al.  Structural Risk Minimization for Character Recognition , 1991, NIPS.

[33]  Geoffrey E. Hinton,et al.  Adaptive Elastic Models for Hand-Printed Character Recognition , 1991, NIPS.

[34]  Patrick J. Grother,et al.  Karhunen Loève feature extraction for neural handwritten character recognition , 1992, Defense, Security, and Sensing.

[35]  Sargur N. Srihari,et al.  Name and Address Block Reader system for tax form processing , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[36]  Michael D. Garris,et al.  NIST Scoring Package User's Guide Release 1.0 | NIST , 1992 .

[37]  Gale L. Martin,et al.  Centered-Object Integrated Segmentation and Recognition of Overlapping Handprinted Characters , 1993, Neural Computation.

[38]  Jim Talley,et al.  Recognizing handwritten phrases from U. S. census forms by combining neural networks and dynamic programming , 1995 .

[39]  Charles L. Wilson,et al.  Binary decision clustering for neural-network-based optical character recognition , 1994, Pattern Recognit..

[40]  Yann LeCun,et al.  Multi-Digit Recognition Using a Space Displacement Neural Network , 1991, NIPS.

[41]  Michael I. Jordan,et al.  Advances in Neural Information Processing Systems 30 , 1995 .

[42]  M. Hirsch,et al.  Differential Equations, Dynamical Systems, and Linear Algebra , 1974 .

[43]  Patrick J. Grother,et al.  Training feed-forward neural networks using conjugate gradients , 1992, Electronic Imaging.

[44]  Daniel J. Hepp.  Recognition of handprinted and cursive words by finding feature correspondences , 1994, Electronic Imaging.

[45]  Patrick J. Grother,et al.  The First Census Optical Character Recognition Systems Conference | NIST , 1992 .

[46]  Paul D. Gader,et al.  Matching database records to handwritten text , 1994, Electronic Imaging.

[47]  Atul Negi,et al.  A correspondence based approach to segmentation of cursive words , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[48]  Michael D. Garris,et al.  Unconstrained handprint recognition using a limited lexicon , 1994, Electronic Imaging.

[49]  Patrick J. Grother,et al.  NIST Form-Based Handprint Recognition System , 1994 .

[50]  Alexander Shustorovich,et al.  Neural network positioning and classification of handwritten characters , 1996, Neural Networks.

[51]  Michael D. Garris,et al.  Component-based handprint segmentation using adaptive writing style model , 1997, Electronic Imaging.

[52]  George Cybenko,et al.  Ill-Conditioning in Neural Network Training Problems , 1993, SIAM J. Sci. Comput..

[53]  James D. Keeler,et al.  Integrated Segmentation and Recognition of Hand-Printed Numerals , 1990, NIPS.

[54]  Donald P. D'Amato.  Machine vision applications in character recognition and industrial inspection : 10-12 February 1992, San Jose, California , 1992 .

[55]  M. Garris.  NIST form-based handprint recognition system , 1994 .

[56]  Geoffrey E. Hinton,et al.  A Learning Algorithm for Boltzmann Machines , 1985, Cogn. Sci..

[57]  Jan Sijbrand,et al.  Properties of center manifolds , 1985 .

[58]  Rama Chellappa,et al.  Design, Integration, and Evaluation of Form-Based Handprint and OCR Systems | NIST , 1996 .

[59]  Franz L. Alt,et al.  Digital Pattern Recognition by Moments , 1962, JACM.

[60]  Yann LeCun,et al.  Efficient Pattern Recognition Using a New Transformation Distance , 1992, NIPS.

[61]  Takuya Kon-no,et al.  Transactions of the American Mathematical Society , 1996 .

[62]  Patrick J. Grother,et al.  Generalized form registration using structure-based techniques , 1996 .

[63]  Harris Drucker,et al.  Boosting Performance in Neural Networks , 1993, Int. J. Pattern Recognit. Artif. Intell..