International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 130 - Number 17 |
Year of Publication: 2015 |
Authors: Sagarika Borah |
10.5120/ijca2015907088 |
Sagarika Borah . Segmentation of Assamese Handwritten Characters based on Projection Profiles. International Journal of Computer Applications. 130, 17 ( November 2015), 12-17. DOI=10.5120/ijca2015907088
The most important part of a character recognition system is segmenting the characters properly and selecting the best features from the characters. This paper describes a character segmentation method for an ANN based character recognition system which is used for recognition of optically scanned handwritten Assamese character. The segmentation of characters are done using horizontal and vertical projections of the hand written text document. For feature extraction the system extracts the geometric features of the characters which are consist of basic line types that are used in the formation of the character skeleton. The feature vector of the training set generated by this system is used to train the recognition system using ANN.