Off-line Odia handwritten numeral recognition using neural network: A comparative analysis

Character recognition is one of the most interesting and challenging research areas in the field of image processing. The recognition rate of handwritten character is still limited due to the presence of large variety of shape, scale and format in hand written characters. A sophisticated handwritten character recognition system demands a better feature extraction technique that would take care of such variety of handwriting. The work proposed in this paper is an attempt to develop recognizer for Odia handwritten numeral digits based on Binarization and discrete cosine transform (DCT) scheme. The recognizer puts emphasis on exploiting the inherit characteristics of Odia numeral images. The system first employs the techniques like thinning, foreground and background noise removal, cropping and size normalization etc., to preprocess the character images. Binarization and DCT technique is employed separately to extract the features from the images. Subsequently, these feature vectors are sent to the neural network classifier. Extensive simulations show that the results are very promising over a standard dataset and the recognition rate for Binarization and DCT are 80.2% and 90%, respectively.

[1]  Amit Choudhary,et al.  Handwritten Numeral Recognition Using Modified BP ANN Structure , 2011 .

[2]  P. Vanaja Ranjan,et al.  Efficient Zone-based Hybrid Feature Extraction Algorithm for Handwritten Numeral Recognition of Kannada Script , 2009, IICAI.

[3]  Tusar Kanti Mishra,et al.  A comparative analysis of image transformations for handwritten Odia numeral recognition , 2013, 2013 International Conference on Advances in Computing, Communications and Informatics (ICACCI).

[4]  Sebastiano Impedovo,et al.  A novel prototype generation technique for handwriting digit recognition , 2014, Pattern Recognit..

[5]  Fumitaka Kimura,et al.  Modified Quadratic Discriminant Functions and the Application to Chinese Character Recognition , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Gurpreet Singh Lehal,et al.  Segmentation of Horizontally Overlapping Lines in Printed Indian Scripts , 2007 .

[7]  N. Shanthi,et al.  A novel SVM-based handwritten Tamil character recognition system , 2010, Pattern Analysis and Applications.

[8]  Babita Majhi,et al.  Efficient recognition of Odiya numerals using low complexity neural classifier , 2011, 2011 International Conference on Energy, Automation and Signal.

[9]  Yang He,et al.  Alternatives to Variable Duration HMM in Handwriting Recognition , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  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).

[11]  Apurva A. Desai,et al.  Gujarati Handwritten Character Recognition Using Hybrid Method Based On Binary Tree-Classifier And K-Nearest Neighbour , 2013 .

[12]  Manas Ranjan Patra,et al.  Rule Based Evidence Mining for Network Attack , 2007 .

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

[14]  Tomoyuki Hamamura,et al.  An Analytic Word Recognition Algorithm Using a Posteriori Probability , 2007 .

[15]  Apurva A. Desai,et al.  Gujarati handwritten numeral optical character reorganization through neural network , 2010, Pattern Recognit..

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

[17]  Ujjwal Bhattacharya,et al.  An HMM Based Recognition Scheme for Handwritten Oriya Numerals , 2006, 9th International Conference on Information Technology (ICIT'06).

[18]  Hamamura Tomoyuki,et al.  An Analytic Word Recognition Algorithm Using a Posteriori Probability -- Normalization of the number of segmentation candidates , 2007 .

[19]  Amit Choudhary,et al.  Off-line Handwritten Character Recognition Using Features Extracted from Binarization Technique☆ , 2013 .

[20]  Babita Majhi,et al.  Recognition of Offline Handwritten Odia Numerals Using Support Vector Machine , 2015, CI 2015.

[21]  Pradeepta K. Sarangi,et al.  Naïve Bayes Classifier with LU Factorization for Recognition of Handwritten Odia Numerals , 2013 .

[22]  P. S. Satyanarayana,et al.  OCR for Script Identification of Hindi (Devnagari) Numerals using Error Diffusion Halftoning Algorithm with Neural Classifier , 2007 .

[23]  Ching Y. Suen,et al.  A new benchmark on the recognition of handwritten Bangla and Farsi numeral characters , 2009, Pattern Recognit..