RESEARCH OF IMAGE MATCHING ALGORITHM BASED ON ROTATION VECTOR FIELD

RESEARCH OF IMAGE MATCHING ALGORITHM BASED ON ROTATION VECTOR FIELD

A rotation invariant image matching algorithm is introduced in this paper. The feature descriptor of feature points is calculated in polar coordinate system which achieves rotation invariant. The Wallis filter and image edge extraction are applied to reduce the influence of noise an light difference...

Full description

Bibliographic Details
Main Author: Y. S. Duan
Format: Article
Language:English
Published: Copernicus Publications 2012-07-01
Series:The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:http://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XXXIX-B4/123/2012/isprsarchives-XXXIX-B4-123-2012.pdf
id doaj-bcfd2bfef39e41bab501d5aff6b12d56
record_format Article
spelling doaj-bcfd2bfef39e41bab501d5aff6b12d562020-11-24T21:48:40ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342012-07-01XXXIX-B412312510.5194/isprsarchives-XXXIX-B4-123-2012RESEARCH OF IMAGE MATCHING ALGORITHM BASED ON ROTATION VECTOR FIELDY. S. Duan0School of Remote Sensing and Information Engineering, Wuhan University, 129 Luoyu Road, Wuhan 430079, ChinaA rotation invariant image matching algorithm is introduced in this paper. The feature descriptor of feature points is calculated in polar coordinate system which achieves rotation invariant. The Wallis filter and image edge extraction are applied to reduce the influence of noise an light difference. After constructing the image feature vectors, the potential correspondences are found firstly and then the Generalized Hough Transform (GHT) is used to purify the matching result . The experiment results of three data sets show that the method is robust to image rotation, time and space efficient and is sufficient to produce matching points which can be used as initial values for further accurate image matching.http://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XXXIX-B4/123/2012/isprsarchives-XXXIX-B4-123-2012.pdf
collection DOAJ
language English
format Article
sources DOAJ
author Y. S. Duan
spellingShingle Y. S. Duan
RESEARCH OF IMAGE MATCHING ALGORITHM BASED ON ROTATION VECTOR FIELD
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
author_facet Y. S. Duan
author_sort Y. S. Duan
title RESEARCH OF IMAGE MATCHING ALGORITHM BASED ON ROTATION VECTOR FIELD
title_short RESEARCH OF IMAGE MATCHING ALGORITHM BASED ON ROTATION VECTOR FIELD
title_full RESEARCH OF IMAGE MATCHING ALGORITHM BASED ON ROTATION VECTOR FIELD
title_fullStr RESEARCH OF IMAGE MATCHING ALGORITHM BASED ON ROTATION VECTOR FIELD
title_full_unstemmed RESEARCH OF IMAGE MATCHING ALGORITHM BASED ON ROTATION VECTOR FIELD
title_sort research of image matching algorithm based on rotation vector field
publisher Copernicus Publications
series The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
issn 1682-1750
2194-9034
publishDate 2012-07-01
description A rotation invariant image matching algorithm is introduced in this paper. The feature descriptor of feature points is calculated in polar coordinate system which achieves rotation invariant. The Wallis filter and image edge extraction are applied to reduce the influence of noise an light difference. After constructing the image feature vectors, the potential correspondences are found firstly and then the Generalized Hough Transform (GHT) is used to purify the matching result . The experiment results of three data sets show that the method is robust to image rotation, time and space efficient and is sufficient to produce matching points which can be used as initial values for further accurate image matching.
url http://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XXXIX-B4/123/2012/isprsarchives-XXXIX-B4-123-2012.pdf
work_keys_str_mv AT ysduan researchofimagematchingalgorithmbasedonrotationvectorfield
_version_ 1725890924324585472

Similar Items