Home // ACHI 2020, The Thirteenth International Conference on Advances in Computer-Human Interactions // View article

Handedness Detection Based on Drawing Patterns using Machine Learning Techniques

Authors:
Jungpil Shin
Md Abdur Rahim

Keywords: Handedness; Handwriting; Drawing Pattern; Support Vector Machine (SVM).

Abstract:
Handedness detection has an effective role in classifying different criminal suspects into specific categories according to soft biometric properties. It determines human motor skills that are performed with the dominant hand while doing everyday activities such as writing and throwing. In this context, this paper offers a system that extracts the characteristics of a person's drawing patterns and uses these features to perform handwriting classifications with regards to handedness. For this, we collect left and right hand data and derive various types of parameters such as elapsed time, x-coordinate, y-coordinate, pen pressure, pen orientation, and pen height. We define different features like mean, maximum, minimum, writing pressure, speed, and Dynamic Programming (DP) for handwriting data for analysis. P-value and t-test are calculated for handwriting evaluation. Furthermore, handedness detection is achieved by using a Support Vector Machine (SVM) classifier. The result shows quite encouraging performance that highlights the effectiveness of the proposed system.

Pages: 182 to 185

Copyright: Copyright (c) IARIA, 2020

Publication date: March 22, 2020

Published in: conference

ISSN: 2308-4138

ISBN: 978-1-61208-761-0

Location: Valencia, Spain

Dates: from November 21, 2020 to November 25, 2020