Off-Line Handwritten Odia Character Recognition Using DWT and PCA

In this paper, we propose a new approach for Odia handwritten character recognition based on discrete wavelet transform (DWT) and principal component analysis (PCA). Statistical feature descriptors like mean, standard deviation, energy have been computed from each sub-band of the second level DWT and are served as the primary features. To find the most significant features, PCA is applied. Subsequently, back-propagation neural network (BPNN) is harnessed to perform the classification task. The proposed method is validated on a standard Odia dataset, containing 150 samples from each of the 47 categories. The simulation results offer a recognition rate of 94.8%.

[1]  Tetsushi Wakabayashi,et al.  A System for Off-Line Oriya Handwritten Character Recognition Using Curvature Feature , 2007, 10th International Conference on Information Technology (ICIT 2007).

[2]  Subhagata Chattopadhyay,et al.  Optical Character Recognition using Ant Miner Algorithm: A Case Study on Oriya Character Recognition , 2013 .

[3]  Sargur N. Srihari,et al.  On-Line and Off-Line Handwriting Recognition: A Comprehensive Survey , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Arun K. Pujari,et al.  A New Parallel Thinning Algorithm with Stroke Correction for Odia Characters , 2014 .

[5]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[6]  Banshidhar Majhi,et al.  Brain MR image classification using two-dimensional discrete wavelet transform and AdaBoost with random forests , 2016, Neurocomputing.

[7]  Tusar Kanti Mishra,et al.  Model based odia numeral recognition using fuzzy aggregated features , 2014, Frontiers of Computer Science.

[8]  Debananda Padhi,et al.  Zone Centroid Distance and Standard Deviation Based Feature Matrix for Odia Handwritten Character Recognition , 2013 .

[9]  Gaurav Kumar,et al.  A Detailed Review of Feature Extraction in Image Processing Systems , 2014, 2014 Fourth International Conference on Advanced Computing & Communication Technologies.

[10]  P. K. Patra,et al.  Probabilistic neural network for pattern classification , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[11]  Umapada Pal,et al.  Handwriting Recognition in Indian Regional Scripts: A Survey of Offline Techniques , 2012, TALIP.

[12]  Wilhelm Burger,et al.  Digital Image Processing - An Algorithmic Introduction using Java , 2008, Texts in Computer Science.

[13]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[14]  Umapada Pal,et al.  Text Independent Writer Identification for Oriya Script , 2012, 2012 10th IAPR International Workshop on Document Analysis Systems.

[15]  Ganapati Panda,et al.  A hybrid feature and discriminant classifier for high accuracy handwritten Odia numeral recognition , 2014, 2014 IEEE REGION 10 SYMPOSIUM.

[16]  Bidyut Baran Chaudhuri,et al.  Automatic recognition of printed Oriya script , 2001, Proceedings of Sixth International Conference on Document Analysis and Recognition.

[17]  Tetsushi Wakabayashi,et al.  F-ratio Based Weighted Feature Extraction for Similar Shape Character Recognition , 2009, 2009 10th International Conference on Document Analysis and Recognition.