Fourier Transform to Group Feature on Generated Coarser Contours for Fast 2D Shape Matching

Fourier descriptors are classical global shape descriptors with high matching speed but low accuracy. To obtain higher accuracy, a novel framework for forming Fourier descriptors is proposed and named as MSFDGF (multiscale Fourier descriptor using group feature). MSFDGF achieves multiscale descripti...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yan Zheng, Fanjie Meng, Jie Liu, Baolong Guo, Yang Song, Xuebing Zhang, Ling Wang
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2020
Materias:	Fast 2D shape retrieval fast shape matching MPEG-7 CE-1 Part B shape descriptor Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/6d8d44084f164db8a5d3e268851ccb40
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6d8d44084f164db8a5d3e268851ccb40
record_format	dspace
spelling	oai:doaj.org-article:6d8d44084f164db8a5d3e268851ccb402021-11-19T00:03:26ZFourier Transform to Group Feature on Generated Coarser Contours for Fast 2D Shape Matching2169-353610.1109/ACCESS.2020.2994234https://doaj.org/article/6d8d44084f164db8a5d3e268851ccb402020-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9091798/https://doaj.org/toc/2169-3536Fourier descriptors are classical global shape descriptors with high matching speed but low accuracy. To obtain higher accuracy, a novel framework for forming Fourier descriptors is proposed and named as MSFDGF (multiscale Fourier descriptor using group feature). MSFDGF achieves multiscale description by generating coarser contours. Then, a group of complementary features are extracted on the generated coarser contours. Finally, Fourier transform is performed on the features. MSFDGF-SH is a new global descriptor using the MSFDGF framework and shape histograms. Experiments are conducted on four databases, which are MPEG-7 CE-1 Part B, Swedish Plant Leaf, Kimia 99 and Expanded Articulated Database, to evaluate the performance of MSFDGF-SH. The experimental results show that MSFDGF-SH is an effective and efficient global shape descriptor. This new descriptor has a high accuracy of 87.76%, which exceeds the Shape Tree on the MPEG-7 CE-1 Part B dataset. This is the first Fourier descriptor that surpasses the Shape Tree method in terms of both accuracy and speed on this dataset.Yan ZhengFanjie MengJie LiuBaolong GuoYang SongXuebing ZhangLing WangIEEEarticleFast 2D shape retrievalfast shape matchingMPEG-7 CE-1 Part Bshape descriptorElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 8, Pp 90141-90152 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Fast 2D shape retrieval fast shape matching MPEG-7 CE-1 Part B shape descriptor Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Fast 2D shape retrieval fast shape matching MPEG-7 CE-1 Part B shape descriptor Electrical engineering. Electronics. Nuclear engineering TK1-9971 Yan Zheng Fanjie Meng Jie Liu Baolong Guo Yang Song Xuebing Zhang Ling Wang Fourier Transform to Group Feature on Generated Coarser Contours for Fast 2D Shape Matching
description	Fourier descriptors are classical global shape descriptors with high matching speed but low accuracy. To obtain higher accuracy, a novel framework for forming Fourier descriptors is proposed and named as MSFDGF (multiscale Fourier descriptor using group feature). MSFDGF achieves multiscale description by generating coarser contours. Then, a group of complementary features are extracted on the generated coarser contours. Finally, Fourier transform is performed on the features. MSFDGF-SH is a new global descriptor using the MSFDGF framework and shape histograms. Experiments are conducted on four databases, which are MPEG-7 CE-1 Part B, Swedish Plant Leaf, Kimia 99 and Expanded Articulated Database, to evaluate the performance of MSFDGF-SH. The experimental results show that MSFDGF-SH is an effective and efficient global shape descriptor. This new descriptor has a high accuracy of 87.76%, which exceeds the Shape Tree on the MPEG-7 CE-1 Part B dataset. This is the first Fourier descriptor that surpasses the Shape Tree method in terms of both accuracy and speed on this dataset.
format	article
author	Yan Zheng Fanjie Meng Jie Liu Baolong Guo Yang Song Xuebing Zhang Ling Wang
author_facet	Yan Zheng Fanjie Meng Jie Liu Baolong Guo Yang Song Xuebing Zhang Ling Wang
author_sort	Yan Zheng
title	Fourier Transform to Group Feature on Generated Coarser Contours for Fast 2D Shape Matching
title_short	Fourier Transform to Group Feature on Generated Coarser Contours for Fast 2D Shape Matching
title_full	Fourier Transform to Group Feature on Generated Coarser Contours for Fast 2D Shape Matching
title_fullStr	Fourier Transform to Group Feature on Generated Coarser Contours for Fast 2D Shape Matching
title_full_unstemmed	Fourier Transform to Group Feature on Generated Coarser Contours for Fast 2D Shape Matching
title_sort	fourier transform to group feature on generated coarser contours for fast 2d shape matching
publisher	IEEE
publishDate	2020
url	https://doaj.org/article/6d8d44084f164db8a5d3e268851ccb40
work_keys_str_mv	AT yanzheng fouriertransformtogroupfeatureongeneratedcoarsercontoursforfast2dshapematching AT fanjiemeng fouriertransformtogroupfeatureongeneratedcoarsercontoursforfast2dshapematching AT jieliu fouriertransformtogroupfeatureongeneratedcoarsercontoursforfast2dshapematching AT baolongguo fouriertransformtogroupfeatureongeneratedcoarsercontoursforfast2dshapematching AT yangsong fouriertransformtogroupfeatureongeneratedcoarsercontoursforfast2dshapematching AT xuebingzhang fouriertransformtogroupfeatureongeneratedcoarsercontoursforfast2dshapematching AT lingwang fouriertransformtogroupfeatureongeneratedcoarsercontoursforfast2dshapematching
_version_	1718420673682997248

Fourier Transform to Group Feature on Generated Coarser Contours for Fast 2D Shape Matching

Ejemplares similares