Chain code feature based recognition of handwritten Gujarati numerals
Main Article Content
Abstract
This paper describes chain code based method for handwritten Gujarati numeral recognition. Literature review on Indian OCR indicates that in comparison with Bangla, Hindi, Kannada, Tamil and Telugu scripts, the OCR activities related to Gujarati script is very less. Development of OCR for Gujarati script is quite challenging area for research. In this work, recognition of isolated Gujarati handwritten numerals is performed using chain code based methods. Horizontal scanning and maximum distance from centroid methods are used for deciding the starting point for calculating the chain code sequence. An overall accuracy of 96.37% and 95.62% is obtained using feed forward neural network classifier by the proposed methods respectively. One of the significant contributions of this paper is towards the generation of large and representative database for handwritten Gujarati numerals.
Keywords:Chain code, Gujarati handwritten numeral recognition, Neural network classifier.
Keywords:Chain code, Gujarati handwritten numeral recognition, Neural network classifier.
Downloads
Download data is not yet available.
Article Details
Section
Articles
COPYRIGHT
Submission of a manuscript implies: that the work described has not been published before, that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication, the authors agree to automatic transfer of the copyright to the publisher.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
- The journal allows the author(s) to retain publishing rights without restrictions.
- The journal allows the author(s) to hold the copyright without restrictions.