Holistic cursive word recognition based on perceptual features

This work presents a holistic system for the off-line recognition of cursive words based on the extraction of perceptual features by means of convolution with templates of line segments. The method works directly on gray-level images to avoid losing information due to binarization. Features are represented spatially in order to preserve topological information which is well suited for recognition through convolutional neural networks. Moreover, our feature extraction method does not need to detect baselines to find ascenders and descenders. The system has been tested on small and medium vocabulary sizes demonstrating the feasibility of the proposed method.

[1]  Horst Bunke,et al.  The IAM-database: an English sentence database for offline handwriting recognition , 2002, International Journal on Document Analysis and Recognition.

[2]  Eric Lecolinet,et al.  A Survey of Methods and Strategies in Character Segmentation , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Michael I. Jordan,et al.  The Handbook of Brain Theory and Neural Networks , 2002 .

[4]  Richard O. Duda,et al.  Use of the Hough transformation to detect lines and curves in pictures , 1972, CACM.

[5]  Matthias Zimmermann,et al.  Lexicon reduction using key characters in cursive handwritten words , 1999, Pattern Recognit. Lett..

[6]  Alessandro Vinciarelli,et al.  A survey on off-line Cursive Word Recognition , 2002, Pattern Recognit..

[7]  R. Manmatha,et al.  Holistic word recognition for handwritten historical documents , 2004, First International Workshop on Document Image Analysis for Libraries, 2004. Proceedings..

[8]  Didier Guillevic.  Unconstrained handwriting recognition applied to the processing of bank cheques , 1996 .

[9]  Michael A. Arbib,et al.  The handbook of brain theory and neural networks , 1995, A Bradford book.

[10]  Eric Lecolinet,et al.  Cursive handwriting recognition using the Hough transform and a neural network , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

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

[12]  L. M. Murphy,et al.  Linear feature detection and enhancement in noisy images via the Radon transform , 1986, Pattern Recognit. Lett..

[13]  Nikos Papamarkos,et al.  A window-based inverse Hough transform , 2000, Pattern Recognit..

[14]  Olivier Baret,et al.  Regularities and Singularities in Line Pictures , 1991, Int. J. Pattern Recognit. Artif. Intell..

[15]  David G. Stork,et al.  Pattern Classification , 1973 .

[16]  Jaehwa Park,et al.  An Adaptive Approach to Offline Handwritten Word Recognition , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  Alessandro Vinciarelli,et al.  A Survey On Off-Line Cursive Script Recognition , 2000 .

[18]  Nasser Sherkat,et al.  Word shape analysis for a hybrid recognition system , 1997, Pattern Recognit..

[19]  M. B. Sandler,et al.  A neural network shape recognition system with Hough transform input feature space , 1992 .

[20]  Ching Y. Suen,et al.  Automatic reading of cursive scripts using a reading model and perceptual concepts , 1998, International Journal on Document Analysis and Recognition.

[21]  Roberto Battiti,et al.  Using mutual information for selecting features in supervised neural net learning , 1994, IEEE Trans. Neural Networks.

[22]  Venu Govindaraju,et al.  Holistic Verification of Handwritten Phrases , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[23]  Samy Bengio,et al.  The Handbook of Brain Theory and Neural Networks , 2002 .

[24]  Nikos Papamarkos,et al.  On the gray-scale inverse Hough transform , 2000, Image Vis. Comput..

[25]  Ching Y. Suen,et al.  An HMM-MLP Hybrid Model for Cursive Script Recognition , 2000, Pattern Analysis & Applications.

[26]  Lambert Schomaker,et al.  Finding features used in the human reading of cursive handwriting , 1999, International Journal on Document Analysis and Recognition.

[27]  Cheng-Lin Liu,et al.  Handwritten digit recognition: benchmarking of state-of-the-art techniques , 2003, Pattern Recognit..

[28]  Chong-Ho Choi,et al.  Input feature selection for classification problems , 2002, IEEE Trans. Neural Networks.

[29]  Robert Sabourin,et al.  Large vocabulary off-line handwriting recognition: A survey , 2003, Pattern Analysis & Applications.

[30]  Rajjan Shinghal,et al.  Symbolic/neural recognition of cursive amounts on bank cheques , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[31]  Sargur N. Srihari,et al.  Off-Line Cursive Script Word Recognition , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[32]  Christophe Parisse.  Global Word Shape Processing in Off-Line Recognition of Handwriting , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[33]  Gyeonghwan Kim,et al.  A Lexicon Driven Approach to Handwritten Word Recognition for Real-Time Applications , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[34]  Cheng-Lin Liu,et al.  Directional pattern matching for character recognition revisited , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[35]  Hermann Ney,et al.  On the Probabilistic Interpretation of Neural Network Classifiers and Discriminative Training Criteria , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[36]  Josef Kittler,et al.  A survey of the hough transform , 1988, Comput. Vis. Graph. Image Process..

[37]  Venu Govindaraju,et al.  The Role of Holistic Paradigms in Handwritten Word Recognition , 2009 .