Handwritten Hindi Character Recognition System Using Edge detection & Neural Network
Journal: International Journal of Advanced Technology and Engineering Exploration (IJATEE) (Vol.2, No. 6)Publication Date: 2015-05-30
Authors : Tanuja K; Usha Kumari V; Sushma T M;
Page : 71-75
Keywords : Canny edge detection; Distance Transformation; Feature Extraction; Neural Network.;
Abstract
Handwritten recognition has been one of the active and challenging research areas in the field of Image processing. Most of the current work in these areas is limited to English and a few oriental languages. Handwritten characters are written in various curved & cursive ways with different sizes, orientations, thickness and dimensions which is difficult task to recognize the handwritten characters by machine. In this paper a novel technique for Handwritten Hindi Character Recognition System is implemented using Canny Edge Detection technique and artificial neural network. The steps used for Handwritten Hindi character recognition system are ? 1.Scanning 2.Preprocessing 3.Segmentation 4.Canny operator 5.Distance transformation 6. Feature Extraction 7. Feed Back Propagation of Artificial Neural Network for Recognition. Experimental result shows that this approach provides better results as compared to other techniques performance of the system in 95%.
Other Latest Articles
- Hi-tech Helmet and Accidental Free Transportation System
- Random Particle Swarm Optimization (RPSO) based Intrusion Detection System
- An efficient Association based Optimization technique for Web pages
- An Effective Approach for Indexed Data Access based on Linear Search Technique Using Reference Key Algorithm
- INDOOR AIR QUALITY ASSESSMENT THROUGH MICROBIOLOGICAL METHODS
Last modified: 2015-06-08 22:47:40