Recognition of Eye-Written Characters Using Deep Neural Network

Eye writing is a human–computer interaction tool that translates eye movements into characters using automatic recognition by computers. Eye-written characters are similar in form to handwritten ones, but their shapes are often distorted because of the biosignal’s instability or user mistakes. Vario...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Won-Du Chang, Jae-Hyeok Choi, Jungpil Shin
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	artificial neural network biosignal analysis electrooculogram eye-tracking human–computer interface pattern recognition Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/6bde9ba10603480eb848882869f33092
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6bde9ba10603480eb848882869f33092
record_format	dspace
spelling	oai:doaj.org-article:6bde9ba10603480eb848882869f330922021-11-25T16:43:11ZRecognition of Eye-Written Characters Using Deep Neural Network10.3390/app1122110362076-3417https://doaj.org/article/6bde9ba10603480eb848882869f330922021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/22/11036https://doaj.org/toc/2076-3417Eye writing is a human–computer interaction tool that translates eye movements into characters using automatic recognition by computers. Eye-written characters are similar in form to handwritten ones, but their shapes are often distorted because of the biosignal’s instability or user mistakes. Various conventional methods have been used to overcome these limitations and recognize eye-written characters accurately, but difficulties have been reported as regards decreasing the error rates. This paper proposes a method using a deep neural network with inception modules and an ensemble structure. Preprocessing procedures, which are often used in conventional methods, were minimized using the proposed method. The proposed method was validated in a writer-independent manner using an open dataset of characters eye-written by 18 writers. The method achieved a 97.78% accuracy, and the error rates were reduced by almost a half compared to those of conventional methods, which indicates that the proposed model successfully learned eye-written characters. Remarkably, the accuracy was achieved in a writer-independent manner, which suggests that a deep neural network model trained using the proposed method is would be stable even for new writers.Won-Du ChangJae-Hyeok ChoiJungpil ShinMDPI AGarticleartificial neural networkbiosignal analysiselectrooculogrameye-trackinghuman–computer interfacepattern recognitionTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 11036, p 11036 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	artificial neural network biosignal analysis electrooculogram eye-tracking human–computer interface pattern recognition Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	artificial neural network biosignal analysis electrooculogram eye-tracking human–computer interface pattern recognition Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Won-Du Chang Jae-Hyeok Choi Jungpil Shin Recognition of Eye-Written Characters Using Deep Neural Network
description	Eye writing is a human–computer interaction tool that translates eye movements into characters using automatic recognition by computers. Eye-written characters are similar in form to handwritten ones, but their shapes are often distorted because of the biosignal’s instability or user mistakes. Various conventional methods have been used to overcome these limitations and recognize eye-written characters accurately, but difficulties have been reported as regards decreasing the error rates. This paper proposes a method using a deep neural network with inception modules and an ensemble structure. Preprocessing procedures, which are often used in conventional methods, were minimized using the proposed method. The proposed method was validated in a writer-independent manner using an open dataset of characters eye-written by 18 writers. The method achieved a 97.78% accuracy, and the error rates were reduced by almost a half compared to those of conventional methods, which indicates that the proposed model successfully learned eye-written characters. Remarkably, the accuracy was achieved in a writer-independent manner, which suggests that a deep neural network model trained using the proposed method is would be stable even for new writers.
format	article
author	Won-Du Chang Jae-Hyeok Choi Jungpil Shin
author_facet	Won-Du Chang Jae-Hyeok Choi Jungpil Shin
author_sort	Won-Du Chang
title	Recognition of Eye-Written Characters Using Deep Neural Network
title_short	Recognition of Eye-Written Characters Using Deep Neural Network
title_full	Recognition of Eye-Written Characters Using Deep Neural Network
title_fullStr	Recognition of Eye-Written Characters Using Deep Neural Network
title_full_unstemmed	Recognition of Eye-Written Characters Using Deep Neural Network
title_sort	recognition of eye-written characters using deep neural network
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/6bde9ba10603480eb848882869f33092
work_keys_str_mv	AT wonduchang recognitionofeyewrittencharactersusingdeepneuralnetwork AT jaehyeokchoi recognitionofeyewrittencharactersusingdeepneuralnetwork AT jungpilshin recognitionofeyewrittencharactersusingdeepneuralnetwork
_version_	1718413024378748928

Recognition of Eye-Written Characters Using Deep Neural Network

Ejemplares similares