A Multistage Handwritten Marathi Compound Character Recognition Scheme using Neural Networks and Wavelet Features

Compound characters which are one of the features of Marathi script, derived from Devanagari, occur frequently in the script. Recognition of these characters poses challenges to the researchers due to their complex structure. This paper presents a novel approach for recognition of unconstrained handwritten Marathi compound characters. The recognition is carried out using multistage feature extraction and classification scheme. The initial stages of feature extraction are based upon the structural features and the classification of the characters is done according to the structural parameters into 24 classes. The final stage of feature extraction employs wavelet transform. Single level wavelet decomposition is used to generate the approximation coefficients which are used as features. These coefficients are further modified and then used as another set of features. Both the wavelet approximation features as well as the modified wavelet features are applied to neural network for recognition. A separate neural network block is built for each of the 24 classes. The average recognition rate is found to be 96.14% and 94.22% respectively for training and testing samples with wavelet approximation features and 98.68% and 96.23% respectively for training and testing samples with modified wavelet features.

[1]  Tetsushi Wakabayashi,et al.  Handwritten Bangla Compound Character Recognition Using Gradient Feature , 2007, 10th International Conference on Information Technology (ICIT 2007).

[2]  Tetsushi Wakabayashi,et al.  Comparative Study of Devnagari Handwritten Character Recognition Using Different Feature and Classifiers , 2009, 2009 10th International Conference on Document Analysis and Recognition.

[3]  Mahantapas Kundu,et al.  Combining Multiple Feature Extraction Techniques for Handwritten Devnagari Character Recognition , 2008, 2008 IEEE Region 10 and the Third international Conference on Industrial and Information Systems.

[4]  Sankar K. Pal,et al.  International Journal of Signal Processing , Image Processing and Pattern Recognition , 2008 .

[5]  Veena Bansal.  Integrating Knowledge Sources in Devanagari Text Recognition , 1999 .

[6]  B. B. Chaudhuri.  Digital document processing : major directions and recent advances , 2006 .

[7]  Bidyut Baran Chaudhuri,et al.  A system for Indian postal automation , 2005, Eighth International Conference on Document Analysis and Recognition (ICDAR'05).

[8]  Arun K. Pujari,et al.  An intelligent character recognizer for Telugu scripts using multiresolution analysis and associative memory , 2004, Image Vis. Comput..

[9]  Fumitaka Kimura,et al.  Indian Multi-Script Full Pin-code String Recognition for Postal Automation , 2009, 2009 10th International Conference on Document Analysis and Recognition.

[10]  Ujjwal Bhattacharya,et al.  A Two Stage Recognition Scheme for Handwritten Tamil Characters , 2007, Ninth International Conference on Document Analysis and Recognition (ICDAR 2007).

[11]  Bidyut Baran Chaudhuri,et al.  Indian script character recognition: a survey , 2004, Pattern Recognit..

[12]  Bidyut Baran Chaudhuri,et al.  Segmentation of touching characters in printed Devnagari and Bangla scripts using fuzzy multifactorial analysis , 2001, Proceedings of Sixth International Conference on Document Analysis and Recognition.

[13]  Santanu Chaudhury,et al.  Devnagari numeral recognition by combining decision of multiple connectionist classifiers , 2002 .

[14]  Fumitaka Kimura,et al.  Oriya handwritten numeral recognition system , 2005, Eighth International Conference on Document Analysis and Recognition (ICDAR'05).

[15]  Tetsushi Wakabayashi,et al.  Off-Line Handwritten Character Recognition of Devnagari Script , 2007 .

[16]  Tetsushi Wakabayashi,et al.  Accuracy Improvement of Devnagari Character Recognition Combining SVM and MQDF , 2008 .

[17]  Veena Bansal,et al.  On how to describe shapes of Devanagari characters and use them for recognition , 1999, Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR '99 (Cat. No.PR00318).

[18]  Hiromichi Fujisawa,et al.  Machine Learning in Document Analysis and Recognition , 2008, Studies in Computational Intelligence.

[19]  Bidyut Baran Chaudhuri,et al.  A complete printed Bangla OCR system , 1998, Pattern Recognit..

[20]  T. R. Sontakke,et al.  Rotation, scale and translation invariant handwritten Devanagari numeral character recognition using general fuzzy neural network , 2007, Pattern Recognit..