Handwritten Numeral Recognition of Six Popular Indian Scripts

Authors:
U. Pal;N. Sharma;T. Wakabayashi;F. Kimura
Affiliations:
Indian Statistical Institute, Kolkata-108, India;Mie University;Indian Statistical Institute, Kolkata-108, India;Mie University
Venue:
ICDAR '07 Proceedings of the Ninth International Conference on Document Analysis and Recognition - Volume 02
Year:
2007

Citing 0
Cited 6

A new benchmark on the recognition of handwritten Bangla and Farsi numeral characters

Pattern Recognition
Recognition of Numeric Postal Codes from Multi-script Postal Address Blocks

PReMI '09 Proceedings of the 3rd International Conference on Pattern Recognition and Machine Intelligence
A novel framework for automatic sorting of postal documents with multi-script address blocks

Pattern Recognition
Handwriting Recognition in Indian Regional Scripts: A Survey of Offline Techniques

ACM Transactions on Asian Language Information Processing (TALIP)
Bangla date field extraction in offline handwritten documents

Proceeding of the workshop on Document Analysis and Recognition
A hybrid approach for automatic recognition of handwritten devanagari numerals

International Journal of Hybrid Intelligent Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

India is a multi-lingual multi-script country but there is not much work towards handwritten character recognition of Indian languages. In this paper we propose a modified quadratic classifier based scheme towards the recognition of off-line handwritten numerals of six popular Indian scripts. Here we consider Devnagari, Bangla, Telugu, Oriya, Kannada and Tamil scripts for our experiment. The features used in the classifier are obtained from the directional information of the numerals. For feature computation, the bounding box of a numeral is segmented into blocks and the directional features are computed in each of the blocks. These blocks are then down sampled by a Gaussian filter and the features obtained from the down sampled blocks are fed to a modified quadratic classifier for recognition. Here we have used two sets of feature. We have used 64 dimensional features for high-speed recognition and 400 dimensional features for high-accuracy recognition in our proposed system. A five-fold cross validation technique has been used for result computation and we obtained 99.56%, 98.99%, 99.37%, 98.40%, 98.71% and 98.51% accuracy from Devnagari, Bangla, Telugu, Oriya, Kannada, and Tamil scripts, respectively.