Comparative Performance Analysis of Feature(S)-Classifier Combination for Devanagari Optical Character Recognition System
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2014, Vol 5, Issue 6
Abstract
This paper presents a comparative performance analysis of feature(s)-classifier combination for Devanagari optical character recognition system. For performance evaluation, three classifiers namely support vector machines, artificial neural networks and k-nearest neighbors, and seven feature extraction approaches viz. profile direction codes, transition, zoning, directional distance distribution, Gabor filter, discrete cosine transform and gradient features have been used. The first four features have been used jointly as statistical features. The performance has also been evaluated by using the combination of these feature extraction approaches. In addition, performance evaluation has also been done by varying the feature vector length of Gabor and DCT features. For training the classifiers, 7000 samples of first 70 classes (out of 942 classes), recognized in the earlier work have been used. Such a large number of classes are due to the horizontal and vertical fusion/overlapping characters. We have chosen first 70 classes as their percentage contribution out of 942 classes has found to be 96.69%. For testing, 1400 samples have been collected separately. A corpus of 25 books has been used for sample collection. Classifiers trained on different features, have been compared for performance evaluation. It has been found that support vector machines trained with Gradient features provide the classification correctness of 99.429%, and there is no significant increase in the performance with the increase in the feature vector length.
Authors and Affiliations
Jasbir Singh, Gurpreet Lehal
Keywords
Related Articles
- EP ID EP88676
- DOI 10.14569/IJACSA.2014.050608
- Views 128
- Downloads 0
Wi-Fi Redux: Never Trust Untrusted Networks
This study analyzes the dangers posed to computer user information and their equipment as they connect to untrusted networks, such as those found in coffee shops. Included in this study is a virtualized lab consisting of...
Fuzzy Data Mining for Autism Classification of Children
Autism is a development condition linked with healthcare costs, therefore, early screening of autism symptoms can cut down on these costs. The autism screening process involves presenting a series of questions for parent...
Texture Analysis on Image Motif of Endek Bali using K-Nearest Neighbor Classification Method
Endek fabric Bali is one form of craft woven fabric of Balinese society. Endek fabric has a variety of motifs or designs, a lot of people does not know that Endek have the type based on the design motif. In this research...
An enhanced Scheme for Reducing Vertical handover latency
Authentication in vertical Hand over is a demanding research problem. Countless methods are commenced but all of them have insufficiencies in term of latency and packet loss. Standard handover schemes (MIPv4, MIPv6...
Cyber Romance Scam Victimization Analysis using Routine Activity Theory Versus Apriori Algorithm
The advance new digital era nowadays has led to the increasing cases of cyber romance scam in Malaysia. These technologies have offered both opportunities and challenge, depending on the purpose of the user. To face this...