A Sequential Handwriting Recognition Model Based on a Dynamically Configurable CRNN

Handwriting recognition refers to recognizing a handwritten input that includes character(s) or digit(s) based on an image. Because most applications of handwriting recognition in real life contain sequential text in various languages, there is a need to develop a dynamic handwriting recognition sys...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ahmed AL-Saffar, Suryanti Awang, Wafaa AL-Saiagh, Ahmed Salih AL-Khaleefa, Saad Adnan Abed
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	handwriting recognition Neural Architecture Search (NAS), configuration search metaheuristics optimization deep learning Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/a02416b3edd44d208e3a78993310eb03
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a02416b3edd44d208e3a78993310eb03
record_format	dspace
spelling	oai:doaj.org-article:a02416b3edd44d208e3a78993310eb032021-11-11T19:15:27ZA Sequential Handwriting Recognition Model Based on a Dynamically Configurable CRNN10.3390/s212173061424-8220https://doaj.org/article/a02416b3edd44d208e3a78993310eb032021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7306https://doaj.org/toc/1424-8220Handwriting recognition refers to recognizing a handwritten input that includes character(s) or digit(s) based on an image. Because most applications of handwriting recognition in real life contain sequential text in various languages, there is a need to develop a dynamic handwriting recognition system. Inspired by the neuroevolutionary technique, this paper proposes a Dynamically Configurable Convolutional Recurrent Neural Network (DC-CRNN) for the handwriting recognition sequence modeling task. The proposed DC-CRNN is based on the Salp Swarm Optimization Algorithm (SSA), which generates the optimal structure and hyperparameters for Convolutional Recurrent Neural Networks (CRNNs). In addition, we investigate two types of encoding techniques used to translate the output of optimization to a CRNN recognizer. Finally, we proposed a novel hybridized SSA with Late Acceptance Hill-Climbing (LAHC) to improve the exploitation process. We conducted our experiments on two well-known datasets, IAM and IFN/ENIT, which include both the Arabic and English languages. The experimental results have shown that LAHC significantly improves the SSA search process. Therefore, the proposed DC-CRNN outperforms the handcrafted CRNN methods.Ahmed AL-SaffarSuryanti AwangWafaa AL-SaiaghAhmed Salih AL-KhaleefaSaad Adnan AbedMDPI AGarticlehandwriting recognitionNeural Architecture Search (NAS), configuration searchmetaheuristics optimizationdeep learningChemical technologyTP1-1185ENSensors, Vol 21, Iss 7306, p 7306 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	handwriting recognition Neural Architecture Search (NAS), configuration search metaheuristics optimization deep learning Chemical technology TP1-1185
spellingShingle	handwriting recognition Neural Architecture Search (NAS), configuration search metaheuristics optimization deep learning Chemical technology TP1-1185 Ahmed AL-Saffar Suryanti Awang Wafaa AL-Saiagh Ahmed Salih AL-Khaleefa Saad Adnan Abed A Sequential Handwriting Recognition Model Based on a Dynamically Configurable CRNN
description	Handwriting recognition refers to recognizing a handwritten input that includes character(s) or digit(s) based on an image. Because most applications of handwriting recognition in real life contain sequential text in various languages, there is a need to develop a dynamic handwriting recognition system. Inspired by the neuroevolutionary technique, this paper proposes a Dynamically Configurable Convolutional Recurrent Neural Network (DC-CRNN) for the handwriting recognition sequence modeling task. The proposed DC-CRNN is based on the Salp Swarm Optimization Algorithm (SSA), which generates the optimal structure and hyperparameters for Convolutional Recurrent Neural Networks (CRNNs). In addition, we investigate two types of encoding techniques used to translate the output of optimization to a CRNN recognizer. Finally, we proposed a novel hybridized SSA with Late Acceptance Hill-Climbing (LAHC) to improve the exploitation process. We conducted our experiments on two well-known datasets, IAM and IFN/ENIT, which include both the Arabic and English languages. The experimental results have shown that LAHC significantly improves the SSA search process. Therefore, the proposed DC-CRNN outperforms the handcrafted CRNN methods.
format	article
author	Ahmed AL-Saffar Suryanti Awang Wafaa AL-Saiagh Ahmed Salih AL-Khaleefa Saad Adnan Abed
author_facet	Ahmed AL-Saffar Suryanti Awang Wafaa AL-Saiagh Ahmed Salih AL-Khaleefa Saad Adnan Abed
author_sort	Ahmed AL-Saffar
title	A Sequential Handwriting Recognition Model Based on a Dynamically Configurable CRNN
title_short	A Sequential Handwriting Recognition Model Based on a Dynamically Configurable CRNN
title_full	A Sequential Handwriting Recognition Model Based on a Dynamically Configurable CRNN
title_fullStr	A Sequential Handwriting Recognition Model Based on a Dynamically Configurable CRNN
title_full_unstemmed	A Sequential Handwriting Recognition Model Based on a Dynamically Configurable CRNN
title_sort	sequential handwriting recognition model based on a dynamically configurable crnn
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/a02416b3edd44d208e3a78993310eb03
work_keys_str_mv	AT ahmedalsaffar asequentialhandwritingrecognitionmodelbasedonadynamicallyconfigurablecrnn AT suryantiawang asequentialhandwritingrecognitionmodelbasedonadynamicallyconfigurablecrnn AT wafaaalsaiagh asequentialhandwritingrecognitionmodelbasedonadynamicallyconfigurablecrnn AT ahmedsalihalkhaleefa asequentialhandwritingrecognitionmodelbasedonadynamicallyconfigurablecrnn AT saadadnanabed asequentialhandwritingrecognitionmodelbasedonadynamicallyconfigurablecrnn AT ahmedalsaffar sequentialhandwritingrecognitionmodelbasedonadynamicallyconfigurablecrnn AT suryantiawang sequentialhandwritingrecognitionmodelbasedonadynamicallyconfigurablecrnn AT wafaaalsaiagh sequentialhandwritingrecognitionmodelbasedonadynamicallyconfigurablecrnn AT ahmedsalihalkhaleefa sequentialhandwritingrecognitionmodelbasedonadynamicallyconfigurablecrnn AT saadadnanabed sequentialhandwritingrecognitionmodelbasedonadynamicallyconfigurablecrnn
_version_	1718431601091674112

A Sequential Handwriting Recognition Model Based on a Dynamically Configurable CRNN

Ejemplares similares