Interactive Part Segmentation Using Edge Images

As more and more fields utilize deep learning, there is an increasing demand to make suitable training data for each field. The existing interactive object segmentation models can easily make the mask label data because these can accurately segment the area of the target object through user interact...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ju-Young Oh, Jung-Min Park
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	interactive segmentation part segmentation object segmentation edge image convolutional neural network 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/edf8693ba1f94c4dbe6b530abba1b393
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:edf8693ba1f94c4dbe6b530abba1b393
record_format	dspace
spelling	oai:doaj.org-article:edf8693ba1f94c4dbe6b530abba1b3932021-11-11T15:10:27ZInteractive Part Segmentation Using Edge Images10.3390/app1121101062076-3417https://doaj.org/article/edf8693ba1f94c4dbe6b530abba1b3932021-10-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/10106https://doaj.org/toc/2076-3417As more and more fields utilize deep learning, there is an increasing demand to make suitable training data for each field. The existing interactive object segmentation models can easily make the mask label data because these can accurately segment the area of the target object through user interaction. However, it is difficult to accurately segment the target part in the object using the existing models. We propose a method to increase the accuracy of part segmentation by using the proposed interactive object segmentation model trained only with edge images instead of color images. The results evaluated with the PASCAL VOC Part dataset show that the proposed method can accurately segment the target part compared to the existing interactive object segmentation model and the semantic part-segmentation model.Ju-Young OhJung-Min ParkMDPI AGarticleinteractive segmentationpart segmentationobject segmentationedge imageconvolutional neural networkTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10106, p 10106 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	interactive segmentation part segmentation object segmentation edge image convolutional neural network Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	interactive segmentation part segmentation object segmentation edge image convolutional neural network Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Ju-Young Oh Jung-Min Park Interactive Part Segmentation Using Edge Images
description	As more and more fields utilize deep learning, there is an increasing demand to make suitable training data for each field. The existing interactive object segmentation models can easily make the mask label data because these can accurately segment the area of the target object through user interaction. However, it is difficult to accurately segment the target part in the object using the existing models. We propose a method to increase the accuracy of part segmentation by using the proposed interactive object segmentation model trained only with edge images instead of color images. The results evaluated with the PASCAL VOC Part dataset show that the proposed method can accurately segment the target part compared to the existing interactive object segmentation model and the semantic part-segmentation model.
format	article
author	Ju-Young Oh Jung-Min Park
author_facet	Ju-Young Oh Jung-Min Park
author_sort	Ju-Young Oh
title	Interactive Part Segmentation Using Edge Images
title_short	Interactive Part Segmentation Using Edge Images
title_full	Interactive Part Segmentation Using Edge Images
title_fullStr	Interactive Part Segmentation Using Edge Images
title_full_unstemmed	Interactive Part Segmentation Using Edge Images
title_sort	interactive part segmentation using edge images
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/edf8693ba1f94c4dbe6b530abba1b393
work_keys_str_mv	AT juyoungoh interactivepartsegmentationusingedgeimages AT jungminpark interactivepartsegmentationusingedgeimages
_version_	1718437187356196864

Interactive Part Segmentation Using Edge Images

Ejemplares similares