Weighted Rule-Base Neural Network for Writer Classification through Handwriting Analysis

Abstract

Handwriting Analysis or Graphology is a scientific method of identifying, evaluating and understanding personality through the strokes and patterns revealed by handwriting. It is not document examination, which involves the examination of a sample of handwriting to determine the author. Among the many aspects of handwriting that can serve as scheme to predict personality traits are baseline, size of letters, connecting strokes, spacing between letters, words and lines, starting strokes, end-strokes, word-slant, speed of handwriting, width of margins, and others. In this paper an attempt is made towards the process of personality prediction of the writer through rule-based approach. Based on the personality predicted, the writers are classified as Extroverts, Introverts or Ambiverts. The personality traits revealed by the baseline, the pen pressure, the slant of the writing, the letter „t‟, the letter „p‟ and the lower loop of letter ‟y‟ as found in an individual‟s handwriting are explored. Weights are assigned to the features, extracted from the handwriting, depending on their importance. For decision making a weighted rule-base is designed, which will predict the personality trait of the writer based on these features extracted from the handwriting. A number of rules are formed to make up the rule-base.