Structural Run Based Feature Vector to Classify Printed Tamil Characters Using Neural Network

The core aspiration of this proposed work is to classify Tamil characters inscribed in the palm leaf manuscript using an Artificial Neural Network. Tamil palm leaf manuscript characters in the form of images were processed and segmented using contour-based convex hull bounding box segmentation. The segmented characters were transformed into two forms: Binary Coded Value and the Gray-Level Co-occurrence Matrix (GLCM) feature. The features extracted from the segmented characters were trained by the proposed method of the Modified Adaptive Backpropagation Network (MABPN) algorithm with Shannon activation function. Weight initialization plays an important role in the Backpropagation Neural Network, and hence Nguyen-Widrow weight initialization was introduced to initialize the weights instead of random weight initialization in the proposed method. The models evaluated are MABPN with Shannon activation function using Nguyen-Widrow weight initialization in two forms of input: Binary Coded Value and GLCM feature extracted values. The proposed method with GLCM features as input gave a promising result over binary coded transform.

show abstract

Structural Run Based Feature Vector to Classify Printed Tamil Characters Using Neural Network

Cited by 2 publications

References 18 publications

Survey on Handwritten Characters Recognition in Deep Learning

Survey on Handwritten Characters Recognition in Deep Learning

Classification of Ancient Handwritten Tamil Characters on Palm Leaf Inscription Using Modified Adaptive Backpropagation Neural Network with GLCM Features

Contact Info

Product

Resources

About