Handwritten Hindi Character Recognition System Using Edge detection & 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%.