A hybrid approach for automatic recognition of handwritten devanagari numerals

Automatic recognition of handwritten numerals is difficult because of the huge variety of ways in which people write. Attempts in the literature employ complicated features and recognition engines in trying to cope with the variety of symbols. But this makes the process slow. In this work, a hybrid technique is proposed to achieve the objective of recognition of handwritten Devanagari numerals with less time consumption and without sacrificing recognition accuracy. A database of 11,000 samples is created while ensuring that the samples include a variety of handwritings which are written with different writing instruments and in different colors. The features employed are density features and spline-based edge direction histogram features and combination thereof. The database size is reduced by using clustering to identify similar samples and putting only one representative sample in lieu of the whole cluster as well as reducing the number of features using PCA. This two-fold reduction provides a smaller database. A hybrid technique utilizing artificial Neural Networks A-NN, K-nearest neighbour K-NN and other learning methods is implemented to ensure higher recognition accuracy and speed. These ideas are put together to provide a fast and robust scheme for recognition of handwritten Devanagari numerals with high recognition accuracy, i.e., 99.40% at a reasonable speed.

[1]  M. Hanmandlu,et al.  Fuzzy Based Approach to the Recognition of Multi-Font Numerals , 2003 .

[2]  Madasu Hanmandlu,et al.  Fuzzy Model Based Recognition of Handwritten Hindi Numerals using Bacterial Foraging , 2007, 6th IEEE/ACIS International Conference on Computer and Information Science (ICIS 2007).

[3]  C. Patvardhan,et al.  Handwritten Devnagari Numerals Recognition with Higher Accuracy , 2007, International Conference on Computational Intelligence and Multimedia Applications (ICCIMA 2007).

[4]  Bidyut Baran Chaudhuri,et al.  Recognition of Handprinted Bangla Numerals Using Neural Network Models , 2002, AFSS.

[5]  Fumitaka Kimura,et al.  Recognition of Off-Line Handwritten Devnagari Characters Using Quadratic Classifier , 2006, ICVGIP.

[6]  S. Noushath,et al.  Robust Unconstrained Handwritten Digit Recognition using Radon Transform , 2007, 2007 International Conference on Signal Processing, Communications and Networking.

[7]  Michael Unser,et al.  Splines: a perfect fit for signal and image processing , 1999, IEEE Signal Process. Mag..

[8]  Vasile Palade,et al.  An Efficient Fuzzy Method for Handwritten Character Recognition , 2004, KES.

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

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

[11]  Vasile Palade,et al.  Automatic fuzzy rule base generation for on-line handwritten alphanumeric character recognition , 2005, Int. J. Knowl. Based Intell. Eng. Syst..

[12]  Vasile Palade,et al.  A Customizable Fuzzy System for Offline Handwritten Character Recognition , 2011, Int. J. Artif. Intell. Tools.

[13]  Ashraf Elnagar,et al.  Recognition of handwritten Hindu numerals using structural descriptors , 2003, J. Exp. Theor. Artif. Intell..

[14]  Tetsushi Wakabayashi,et al.  Handwritten Numeral Recognition of Six Popular Indian Scripts , 2007 .

[15]  Madasu Hanmandlu,et al.  Fuzzy model based recognition of handwritten numerals , 2007, Pattern Recognit..

[16]  Hee-Joong Kang.  Combining multiple classifiers based on third-order dependency for handwritten numeral recognition*1 , 2003, Pattern Recognit. Lett..