Devanagari Isolated Character Recognition by using Statistical features ( Foreground Pixels Distribution, Zone Density and Background Directional Distribution feature and SVM Classifier)
Journal Title: International Journal on Computer Science and Engineering - Year 2011, Vol 3, Issue 6
Abstract
In this paper, we present a methodology for off-line Isolated handwritten Devanagari character recognition. The proposed methodology relies on a three feature extraction techniques. The first technique is based on recursive subdivisions of the character image so that the resulting sub-images at each iteration have balanced (approximately equal) numbers of foreground pixels, as far as this is possible. Second technique is based on the zone density of the pixel and third is based on the directional distribution of neighboring background pixels to foreground pixels. The 314 sized feature vector is form from the three feature extraction techniques for a handwritten Devanagari character. The dataset (12240 samples) of handwritten Devanagari Character, have been prepared by writing the different – 2 people who belongs to different age group and obtained the 94.89 % recognition accuracy
Authors and Affiliations
Mahesh Jangid
Keywords
Related Articles
- EP ID EP145091
- DOI -
- Views 116
- Downloads 0
Shortest Distance Message Broadcasting for an Applications in an irregular Mobile Topologies
This paper introduces data forwarding algorithm for a articular applications within Mobile Adhoc etworks that is based on the concept of electing the neighbor node from a set of esignated nodes. The algorithm, which...
Log Mining Based on Hadoop’s Map and Reduce Technique
In the world of cloud and grid computing Virtual Database Technology (VDB) is one of the effective solutions for integration of data from heterogeneous sources. Hadoop is a large-scale distributed batch processing infras...
Comparative Evaluation of Packet Classification Algorithms, with Implementation
in a realm of ever-increasing Internet connectivity, together with swelling computer security threats, security-cognizant network applications technology is gaining widespread popularity. Packet classifiers are extensive...
Modeling a production system based on flow-shop electrical system
Improving the competitiveness of a company amounts to control its workflow. The purpose of industries is to provide customer satisfaction and maximum production with a minimal cost, which requires the provision of a scie...
Analysis of Selective Routing Strategies for Fault Tolerance In Wireless Sensor Networks
Wireless sensor networks are intended to have large number of sensor nodes which are widely deployed in a distributed environment. Steep increase in number of nodes, which is a deviant to WSN eventually, affects the comm...