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...

Full description

Bibliographic Details
Main Authors: Al-Saffar, Ahmed, Suryanti, Awang, Al-Saiagh, Wafaa, Al-Khaleefa, Ahmed Salih, Abed, Saad Adnan
Format: Article
Language:English
Published: MDPI 2021
Subjects:
Online Access:http://umpir.ump.edu.my/id/eprint/32663/
http://umpir.ump.edu.my/id/eprint/32663/1/A%20sequential%20handwriting%20recognition%20model%20based%20on%20a%20dynamically.pdf
_version_ 1848824079585378304
author Al-Saffar, Ahmed
Suryanti, Awang
Al-Saiagh, Wafaa
Al-Khaleefa, Ahmed Salih
Abed, Saad Adnan
author_facet Al-Saffar, Ahmed
Suryanti, Awang
Al-Saiagh, Wafaa
Al-Khaleefa, Ahmed Salih
Abed, Saad Adnan
author_sort Al-Saffar, Ahmed
building UMP Institutional Repository
collection Online Access
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.
first_indexed 2025-11-15T03:07:20Z
format Article
id ump-32663
institution Universiti Malaysia Pahang
institution_category Local University
language English
last_indexed 2025-11-15T03:07:20Z
publishDate 2021
publisher MDPI
recordtype eprints
repository_type Digital Repository
spelling ump-326632024-01-03T06:40:59Z http://umpir.ump.edu.my/id/eprint/32663/ A sequential handwriting recognition model based on a dynamically configurable CRNN Al-Saffar, Ahmed Suryanti, Awang Al-Saiagh, Wafaa Al-Khaleefa, Ahmed Salih Abed, Saad Adnan QA76 Computer software 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. MDPI 2021-11-02 Article PeerReviewed pdf en cc_by_4 http://umpir.ump.edu.my/id/eprint/32663/1/A%20sequential%20handwriting%20recognition%20model%20based%20on%20a%20dynamically.pdf Al-Saffar, Ahmed and Suryanti, Awang and Al-Saiagh, Wafaa and Al-Khaleefa, Ahmed Salih and Abed, Saad Adnan (2021) A sequential handwriting recognition model based on a dynamically configurable CRNN. Sensors, 21 (21). pp. 1-25. ISSN 1424-8220. (Published) https://doi.org/10.3390/s21217306 https://doi.org/10.3390/s21217306
spellingShingle QA76 Computer software
Al-Saffar, Ahmed
Suryanti, Awang
Al-Saiagh, Wafaa
Al-Khaleefa, Ahmed Salih
Abed, Saad Adnan
A sequential handwriting recognition model based on a dynamically configurable CRNN
title 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_short A sequential handwriting recognition model based on a dynamically configurable CRNN
title_sort sequential handwriting recognition model based on a dynamically configurable crnn
topic QA76 Computer software
url http://umpir.ump.edu.my/id/eprint/32663/
http://umpir.ump.edu.my/id/eprint/32663/
http://umpir.ump.edu.my/id/eprint/32663/
http://umpir.ump.edu.my/id/eprint/32663/1/A%20sequential%20handwriting%20recognition%20model%20based%20on%20a%20dynamically.pdf