Improving Amharic Handwritten Word Recognition Using Auxiliary Task

TL;DR

This paper enhances Amharic handwritten word recognition by integrating an auxiliary task based on alphabet similarities into deep learning models, significantly improving accuracy over baseline methods.

Contribution

It introduces a novel auxiliary task leveraging alphabet similarities to improve deep learning-based Amharic handwritten recognition.

Findings

Recognition accuracy improved significantly with the auxiliary task

Deep learning models outperformed traditional OCR methods

The approach demonstrates potential for other script-specific OCR tasks

Abstract

Amharic is one of the official languages of the Federal Democratic Republic of Ethiopia. It is one of the languages that use an Ethiopic script which is derived from Gee'z, ancient and currently a liturgical language. Amharic is also one of the most widely used literature-rich languages of Ethiopia. There are very limited innovative and customized research works in Amharic optical character recognition (OCR) in general and Amharic handwritten text recognition in particular. In this study, Amharic handwritten word recognition will be investigated. State-of-the-art deep learning techniques including convolutional neural networks together with recurrent neural networks and connectionist temporal classification (CTC) loss were used to make the recognition in an end-to-end fashion. More importantly, an innovative way of complementing the loss function using the auxiliary task from the row-wise similarities of the Amharic alphabet was tested to show a significant recognition improvement over a baseline method. Such findings will promote innovative problem-specific solutions as well as will open insight to a generalized solution that emerges from problem-specific domains.