Feature Detection Based on Significancy of Local Features for Image Matching
Summary :
Feature detection and matching procedure require most of processing time in image matching where the time dramatically increases according to the number of feature points. The number of features is needed to be controlled for specific applications because of their processing time. This paper proposes a feature detection method based on significancy of local features. The feature significancy is computed for all pixels and higher significant features are chosen considering spatial distribution. The method contributes to reduce the number of features in order to match two images with maintaining high matching accuracy. It was shown that this approach was faster about two times in average processing time than FAST detector for natural scene images in the experiments.
- Publication
- IEICE TRANSACTIONS on Information Vol.E104-D No.9 pp.1510-1513
- Publication Date
- 2021/09/01
- Publicized
- 2021/06/03
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2021EDL8048
- Type of Manuscript
- LETTER
- Category
- Pattern Recognition
Authors
TaeWoo KIM
Hanyang Cyber University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
TaeWoo KIM, "Feature Detection Based on Significancy of Local Features for Image Matching" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 9, pp. 1510-1513, September 2021, doi: 10.1587/transinf.2021EDL8048.
Abstract: Feature detection and matching procedure require most of processing time in image matching where the time dramatically increases according to the number of feature points. The number of features is needed to be controlled for specific applications because of their processing time. This paper proposes a feature detection method based on significancy of local features. The feature significancy is computed for all pixels and higher significant features are chosen considering spatial distribution. The method contributes to reduce the number of features in order to match two images with maintaining high matching accuracy. It was shown that this approach was faster about two times in average processing time than FAST detector for natural scene images in the experiments.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2021EDL8048/_p
Copy
@ARTICLE{e104-d_9_1510,
author={TaeWoo KIM, },
journal={IEICE TRANSACTIONS on Information},
title={Feature Detection Based on Significancy of Local Features for Image Matching},
year={2021},
volume={E104-D},
number={9},
pages={1510-1513},
abstract={Feature detection and matching procedure require most of processing time in image matching where the time dramatically increases according to the number of feature points. The number of features is needed to be controlled for specific applications because of their processing time. This paper proposes a feature detection method based on significancy of local features. The feature significancy is computed for all pixels and higher significant features are chosen considering spatial distribution. The method contributes to reduce the number of features in order to match two images with maintaining high matching accuracy. It was shown that this approach was faster about two times in average processing time than FAST detector for natural scene images in the experiments.},
keywords={},
doi={10.1587/transinf.2021EDL8048},
ISSN={1745-1361},
month={September},}
Copy
TY - JOUR
TI - Feature Detection Based on Significancy of Local Features for Image Matching
T2 - IEICE TRANSACTIONS on Information
SP - 1510
EP - 1513
AU - TaeWoo KIM
PY - 2021
DO - 10.1587/transinf.2021EDL8048
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2021
AB - Feature detection and matching procedure require most of processing time in image matching where the time dramatically increases according to the number of feature points. The number of features is needed to be controlled for specific applications because of their processing time. This paper proposes a feature detection method based on significancy of local features. The feature significancy is computed for all pixels and higher significant features are chosen considering spatial distribution. The method contributes to reduce the number of features in order to match two images with maintaining high matching accuracy. It was shown that this approach was faster about two times in average processing time than FAST detector for natural scene images in the experiments.
ER -
English
