Characteristics Detection from Handwriting using Machine Learning

Abstract

In this paper, we have proposed a method that will recognize the characteristics of a person based on handwriting. Handwritten recognition is basically a technique in which the computer takes input in the form of an image or document and interprets handwritten input. We have used the Support Vector Machine (SVM) algorithm in our model. While writing we can control our conscious mind about what to write, but not our subconscious how to write. From a handwritten paragraph, the perspective of the writer's internal mind can be discovered. It is a process of interpreting characteristics from patterns in handwriting. Graphology is the analysis of the physical characteristics and patterns of handwriting with an attempt to identify the writer, indicate the psychological state at the time of writing, or evaluate personality characteristics. The accuracy of handwriting analysis depends on the skills and experience of the graphologists. Handwriting analysis means predicting the behavior from a mannerism in handwriting. But the manual process of handwriting analysis is expensive; sometimes it is not precise and may lead to incorrect results. Thus for reducing the errors and improving accuracy this paper proposes an algorithm to recognize the handwriting which is Support Vector Machine (SVM).