ANALYSIS OF PROPOSED TECHNIQUE FOR GRAPHICAL REPRESENTATION OF ISOLATED CHARACTER USING SVM CLASSIFIER
Journal: International Journal of Engineering Sciences & Research Technology (IJESRT) (Vol.5, No. 11)Publication Date: 2016-11-30
Authors : Shaina; Harpreet Kaur Baja;
Page : 430-437
Keywords : SVM Classifier; Global Transformation; Feature Extraction; SINDHI Character Set; Optical Character Recognition (OCR);
Abstract
A graphical representation is a visual display of data and statistical results. It is more often and effective than presenting data in tabular form. Opti cal Character Recognition (OCR) requires a graphical representation of text to interpret, which usually comes from a scanned image. Support Vector Machine (SVM) describes the concept that how the decision planes are made which helps in defining the decisio n boundaries. In this paper a method of isolated graphical representation has been proposed using SVM Classifier. The performance is measured in the terms of accuracy using different font styles and font sizes. The work is done on Sindhi Character Set. The result shows the accuracy recognition rate achieved with SVM Classifier is much better than existing Global Transformation and Feature Extraction Techniques.
Other Latest Articles
- HYDROCHEMISTRY AND POLLUTION ASSESSMENT OF FRESH WATER LAKES
- A SURVEY: PID OPTIMIZATION FOR AUTOMATIC VOLTAGE REGULATOR
- INVESTIGATION OF THE PROPERTIES OF SOLUTI ON OF VARIATIONAL PROBLEM COUPLED FLOW OF SURFACE AND GROUN DWATERS
- APPLICATION OF THE BRANCH AND BOUND ALGORITHM IN THE PLANNING AND PRODUCTION CONTROL IN A TEXTILE INDUSTRY
- ISSUES ON TRADITIONAL AND MODERN TEXTUAL DOCUMENT CLUSTERING ALGORITHMS
Last modified: 2016-11-18 19:45:45