Deep Learning-Based Engraving Segmentation of 3-D Inscriptions Extracted From the Rough Surface of Ancient Stelae

Ancient stelae are considered important historical sources. However, it is a challenge to recognize the inscriptions carved on stelae that have rough surfaces due to prolonged weathering. In this paper, we propose a deep learning-based method to extract engraved regions from the 3D scanned mesh of a...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ye-Chan Choi, Sheriff Murtala, Beom-Chae Jeong, Kang-Sun Choi
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Cultural heritage relief extraction mesh processing engraving segmentation image segmentation Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/333c7944fb4a4965a54f3ea9f30aeec3
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:333c7944fb4a4965a54f3ea9f30aeec3
record_format	dspace
spelling	oai:doaj.org-article:333c7944fb4a4965a54f3ea9f30aeec32021-11-20T00:01:08ZDeep Learning-Based Engraving Segmentation of 3-D Inscriptions Extracted From the Rough Surface of Ancient Stelae2169-353610.1109/ACCESS.2021.3127229https://doaj.org/article/333c7944fb4a4965a54f3ea9f30aeec32021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9611230/https://doaj.org/toc/2169-3536Ancient stelae are considered important historical sources. However, it is a challenge to recognize the inscriptions carved on stelae that have rough surfaces due to prolonged weathering. In this paper, we propose a deep learning-based method to extract engraved regions from the 3D scanned mesh of a stela. First, the uneven distribution of vertices in the mesh is transformed using a mesh subdivision method such that the vertices in the mesh are uniformly distributed. Then, surface features (depth, concave features, and local surface features) are extracted from the subdivided mesh. The depth represents the basic shape of the mesh and is obtained from the aligned mesh. The concave features effectively represent concave regions by using a Frangi filter, and the local surface features have the spin image technique applied to describe the fine shapes of neighboring vertices relative to a vertex. The mesh and the surface features are rasterized into feature images, and engraved regions are segmented from the feature images by using a FC-DenseNet. Our experiments confirm that the proposed method effectively extracts engraved regions of the inscriptions from the rough surface of a stela and it shows robustness to noisy and extremely abraded characters. The proposed method outperformed the second-best method, obtaining an F1 score, IoU, and SIRI of approximately 2.95%, 3.65%, and 7.53%, respectively.Ye-Chan ChoiSheriff MurtalaBeom-Chae JeongKang-Sun ChoiIEEEarticleCultural heritagerelief extractionmesh processingengraving segmentationimage segmentationElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 153199-153212 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Cultural heritage relief extraction mesh processing engraving segmentation image segmentation Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Cultural heritage relief extraction mesh processing engraving segmentation image segmentation Electrical engineering. Electronics. Nuclear engineering TK1-9971 Ye-Chan Choi Sheriff Murtala Beom-Chae Jeong Kang-Sun Choi Deep Learning-Based Engraving Segmentation of 3-D Inscriptions Extracted From the Rough Surface of Ancient Stelae
description	Ancient stelae are considered important historical sources. However, it is a challenge to recognize the inscriptions carved on stelae that have rough surfaces due to prolonged weathering. In this paper, we propose a deep learning-based method to extract engraved regions from the 3D scanned mesh of a stela. First, the uneven distribution of vertices in the mesh is transformed using a mesh subdivision method such that the vertices in the mesh are uniformly distributed. Then, surface features (depth, concave features, and local surface features) are extracted from the subdivided mesh. The depth represents the basic shape of the mesh and is obtained from the aligned mesh. The concave features effectively represent concave regions by using a Frangi filter, and the local surface features have the spin image technique applied to describe the fine shapes of neighboring vertices relative to a vertex. The mesh and the surface features are rasterized into feature images, and engraved regions are segmented from the feature images by using a FC-DenseNet. Our experiments confirm that the proposed method effectively extracts engraved regions of the inscriptions from the rough surface of a stela and it shows robustness to noisy and extremely abraded characters. The proposed method outperformed the second-best method, obtaining an F1 score, IoU, and SIRI of approximately 2.95%, 3.65%, and 7.53%, respectively.
format	article
author	Ye-Chan Choi Sheriff Murtala Beom-Chae Jeong Kang-Sun Choi
author_facet	Ye-Chan Choi Sheriff Murtala Beom-Chae Jeong Kang-Sun Choi
author_sort	Ye-Chan Choi
title	Deep Learning-Based Engraving Segmentation of 3-D Inscriptions Extracted From the Rough Surface of Ancient Stelae
title_short	Deep Learning-Based Engraving Segmentation of 3-D Inscriptions Extracted From the Rough Surface of Ancient Stelae
title_full	Deep Learning-Based Engraving Segmentation of 3-D Inscriptions Extracted From the Rough Surface of Ancient Stelae
title_fullStr	Deep Learning-Based Engraving Segmentation of 3-D Inscriptions Extracted From the Rough Surface of Ancient Stelae
title_full_unstemmed	Deep Learning-Based Engraving Segmentation of 3-D Inscriptions Extracted From the Rough Surface of Ancient Stelae
title_sort	deep learning-based engraving segmentation of 3-d inscriptions extracted from the rough surface of ancient stelae
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/333c7944fb4a4965a54f3ea9f30aeec3
work_keys_str_mv	AT yechanchoi deeplearningbasedengravingsegmentationof3dinscriptionsextractedfromtheroughsurfaceofancientstelae AT sheriffmurtala deeplearningbasedengravingsegmentationof3dinscriptionsextractedfromtheroughsurfaceofancientstelae AT beomchaejeong deeplearningbasedengravingsegmentationof3dinscriptionsextractedfromtheroughsurfaceofancientstelae AT kangsunchoi deeplearningbasedengravingsegmentationof3dinscriptionsextractedfromtheroughsurfaceofancientstelae
_version_	1718419826591924224

Deep Learning-Based Engraving Segmentation of 3-D Inscriptions Extracted From the Rough Surface of Ancient Stelae

Ejemplares similares