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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Khayati, Mohsine El, Elouahbi, Rachid, Semma, Abdelillah
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916022759456768
author Khayati, Mohsine El
Elouahbi, Rachid
Semma, Abdelillah
author_facet Khayati, Mohsine El
Elouahbi, Rachid
Semma, Abdelillah
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_18060
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Embedded ConvNet Ensembles: A Lightweight Approach to Recognize Arabic Handwritten Characters
Khayati, Mohsine El
Elouahbi, Rachid
Semma, Abdelillah
Computer Vision and Pattern Recognition
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.
title Embedded ConvNet Ensembles: A Lightweight Approach to Recognize Arabic Handwritten Characters
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.18060