Please use this identifier to cite or link to this item:
|Title:||On extraction of features for handwritten Odia numeral recognition in transformed domain|
|Keywords:||handwritten character recognition|
transformed domain feature
|Abstract:||Recognition of handwritten scripts has always been a challenging task before the character recognition community. The difficulty lies in the fact that different individuals have different writing styles and hence there is a lot of intra-class pattern variation. Several feature extraction techniques based on statistical, structural properties have been reported in literature. We, in this paper, propose a number of image transformation based feature extraction techniques such as, Slantlet transform based, Stockwell transform based, and Gabor-wavelet based transformed domain features for offline Odia handwritten numeral recognition. The performances of the proposed methods are evaluated on ISI Kolkata Odia numeral database with a nearest neighbor classifier and the recognition accuracies are reported. � 2015 IEEE.|
|Appears in Collections:||Research Publications|
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.