Tifinagh-IRCAM Handwritten character recognition using Deep learning

TL;DR

This paper presents a deep learning-based system for recognizing handwritten Amazigh Tifinagh characters, utilizing a custom dataset of 3,366 images from 102 writers to improve recognition accuracy.

Contribution

The study introduces a new dataset of Tifinagh handwritten characters and applies deep learning techniques to enhance recognition performance.

Findings

Created a dataset with 3,366 images from 102 writers

Normalized and centered characters in 28x28 images

Demonstrated the effectiveness of deep learning for Tifinagh recognition

Abstract

In this paper, we exploit the benefits of the deep learning approach to design an efficient system of Amazigh handwritten recognition. Indeed, this approach has proved a greater efficiency in the various domains, especially recognition tasks. However, to take full advantage of this approach it's necessary to construct an adequate dataset of training and testing that represent faithfully the concerned problem. To this end, we have prepared our dataset of 102 writers each one contains 33 characters of IRCAM-Tifinagh. Inspired by the MNIST database, the set of characters is size-normalized and centered in a fixed-size image. The resulting is a grey level image of size 28x28, where the black color is the non-color of the character. The number of images produced after this preprocessing step is 3,366.