Implementation of Linear Discriminant Analysis for Odia Numeral Recognition

In recent time the character recognition attract the attention of the researchers significantly as it has vast application in several fields. The process of converting input text images into machine understandable code or text is known as optical character recognition. In this paper we have devolved an efficient OCR for recognition of Odia Numerals using Linear Discriminant Analysis and compare the result with principal component analysis. Finally we conclude that LDA has a better recognition accuracy over PCA due to dimensionality reduction.

[1]  Pradeepta K. Sarangi,et al.  Recognition of Isolated Handwritten Oriya Numerals using Hopfield Neural Network , 2012 .

[2]  Sanghamitra Mohanty.  Pattern Recognition in Alphabets of Oriya Language Using Kohonen Neural Network , 1998, Int. J. Pattern Recognit. Artif. Intell..

[3]  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).

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

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

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

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

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