High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

Handwriting Recognition and Character Prediction using Neural Networks

Author(s):

Sudhanshu Vohra , Maharaja Agrasen Institute of Technology; Savita Sharma, Maharaja Agrasen Institute of Technology; Priyesh Mishra, Maharaja Agrasen Institute of Technology; Sahil Koli, Maharaja Agrasen Institute of Technology

Keywords:

Handwriting Analysis, Graphology, Graphologists, Behavioral Analysis, Characteristic Traits, Artificial Neural Network

Abstract

Handwriting Analysis or Graphology is a scientific method of producing a personality profile of the writer by examining the characteristic traits by identifying, evaluating the strokes and patterns of the handwriting. Handwriting reveals the true personality including emotional outlay, fears, honesty, defences and many others. Professional handwriting examiners are known as graphologists, they predict the personality of a writer by just examining even a short piece of hand writing. Accuracy of handwriting analysis depends on skills of the graphologists, a skilled graphologists would come at a greater cost and human intervention in handwriting analysis is prone to fatigue, although it’s effective. Hence the proposed methodology focuses on developing a tool for behavioral analysis which can predict the personality traits automatically with the aid of a computer without the human intervention. In this paper a method has been proposed to predict the personality of a person from the baseline, the pen pressure and strokes by examining the numbers ‘0’, ‘1’, ‘2’, ‘3’, ‘4’, ‘5, ‘6’, ‘7’, ‘8’, ‘9’and the letters ‘s’, ‘u’, ’d’, ’o’, ’y’, ’t’, ’b’, ‘p’ through an individual‘s handwriting. These parameters are the inputs to the Artificial Neural Network which outputs the personality trait of the writer. The performance is measured by examining multiple samples.

Other Details

Paper ID: IJSRDV6I21810
Published in: Volume : 6, Issue : 2
Publication Date: 01/05/2018
Page(s): 3601-3604

Article Preview

Download Article