Machine learning approach for bipolar disorder analysis and recognition based on handwriting digital images

Document Type : Original Article

Authors

1 Islamic Azad university of Science and research of Tehran, Iran

2 Islamic Azad University (IAU) - Islamic Azad University (IAU), Science and Research Branch, Iran

3 University of Houston, Department of Biomedical Engineering, USA

Abstract

In some cases, handwriting is a manifestation of the human mind, and it can reveal various psychological characteristics and mental disorders. Among these disorders, bipolar disorder is a well-known and widely studied condition in cognitive science and psychotherapy, and it can be detected in handwriting. In this research, we applied image processing techniques to analyze the handwriting characteristics of people with bipolar disorder based on their responses to a survey. We also proposed a machine learning model that can classify whether a person has bipolar disorder or not by using their handwriting as an input.

Keywords

Main Subjects

AUT Journal of Mathematics and Computing

Articles in Press, Accepted Manuscript
Available Online from 14 April 2024

Files

Share

How to cite

Statistics