Embedded ConvNet Ensembles: A Lightweight Approach to Recognize Arabic Handwritten Characters

TL;DR

This paper proposes lightweight embedded ConvNet ensembles for Arabic handwritten character recognition, achieving high accuracy with reduced computational cost suitable for resource-limited devices.

Contribution

It introduces a combination of lightweight ConvNet models and ensemble techniques, demonstrating improved performance in Arabic handwritten character recognition.

Findings

Embedded models achieve accuracy comparable to heavier architectures.

Ensemble learning enhances performance with modest computational overhead.

Soft voting ensemble yields the best results.

Abstract

Arabic Handwritten Character Recognition (AHCR) has recently advanced significantly with deep Convolutional Neural Networks (ConvNets). However, many models in the literature are deep and computationally expensive in terms of parameters and FLOPs, limiting their deployment on resource-constrained devices, which are increasingly common. This study addresses this gap by proposing a combination of lightweight embedded ConvNet models and ensemble learning techniques. Extensive experiments were conducted to identify best practices in AHCR, considering training hyperparameters, learning strategies, model choices, and ensemble methods. Results show that embedded models can achieve accuracy comparable to, or even surpassing, heavier architectures. Ensemble learning further enhances performance with only modest computational overhead, particularly under challenging training scenarios. Among the ensembling strategies, soft voting yielded the best overall results.