Handwriting Recognition in Indian Regional Scripts: A Survey of Offline Techniques
ACM Transactions on Asian Language Information Processing (TALIP)
A comparison of machine learning techniques for handwritten |Xam word recognition
Proceedings of the South African Institute for Computer Scientists and Information Technologists Conference
Hi-index | 0.00 |
The Handwriting character recognition (HCR) for Indian Languages is an important problem where there is relatively little work has been done. In this paper, we investigate the use of moments features on Kannada Kagunita. Kannada characters are curved in nature with some kind of symmetric structure observed in the shape. This information can be best extracted as a feature if we extract moment features from the directional images. To recognize a Kagunita, we need to identify the vowel and the consonant present in the image. So we are finding 4 directional images using Gabor wavelets from the dynamically preprocessed original image. We analyze the Kagunita set and identify the regions with vowel information and consonant information and cut these portions from the preprocessed original image and form a set of cut images. We then extract moments features from them. These features are trained and tested for both vowel and Kagunita recognition on Multi Layer Perceptron with Back Propagation Neural Network. The recognition results for vowels is average 85% and consonants is 59% when tested on separate test data with moments features from directional images and cut images.