Multi-script handwritten digit recognition using multi-task learning

Abstract

Handwritten digit recognition is one of the extensively studied areas in machine learning. Apart from the wider research on handwritten digit recognition on MNIST dataset, there are many other research works on various script recognition. However, it is not very common for multi-script digit recognition which encourages the development of robust and multipurpose systems. Additionally, working on multi-script digit recognition enables multi-task learning. It is evident that multi-task learning improves model performance through inductive transfer using the information contained in related tasks. Therefore, in this study multi-script handwritten digit recognition using multi-task learning is proposed to be investigated. As a specific case of demonstrating the solution to the problem, Amharic handwritten character recognition is also experimentally tested. The handwritten digits of three scripts including Latin, Arabic, and Kannada are studied to show that multi-task models with a reformulation of the individual tasks have shown promising results. In this study, a novel approach of using the individual tasks predictions was proposed to help the classification performance. These research findings have outperformed the baseline and the conventional multi-task learning models. More importantly, it avoided the need for weighting the different losses of the tasks, which is one of the challenges in multi-task learning.