A New Framework for Constructing Accurate Affine Invariant Regions
Summary :
In this study, we propose a simple, yet general and powerful framework for constructing accurate affine invariant regions. In our framework, a method for extracting reliable seed points is first proposed. Then, regions which are invariant to most common affine transformations can be extracted from seed points by two new methods the Path Growing (PG) or the Thresholding Seeded Growing Region (TSGR). After that, an improved ellipse fitting method based on the Direct Least Square Fitting (DLSF) is used to fit the irregularly-shaped contours from the PG or the TSGR to obtain ellipse regions as the final invariant regions. In the experiments, our framework is first evaluated by the criterions of Mikolajczyk's evaluation framework [1], and then by near-duplicate detection problem [2]. Our framework shows its superiorities to the other detectors for different transformed images under Mikolajczyk's evaluation framework and the one with TSGR also gives satisfying results in the application to near-duplicate detection problem.
- Publication
- IEICE TRANSACTIONS on Information Vol.E90-D No.11 pp.1831-1840
- Publication Date
- 2007/11/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1093/ietisy/e90-d.11.1831
- Type of Manuscript
- PAPER
- Category
- Image Recognition, Computer Vision
Authors
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
Li TIAN, Sei-ichiro KAMATA, "A New Framework for Constructing Accurate Affine Invariant Regions" in IEICE TRANSACTIONS on Information,
vol. E90-D, no. 11, pp. 1831-1840, November 2007, doi: 10.1093/ietisy/e90-d.11.1831.
Abstract: In this study, we propose a simple, yet general and powerful framework for constructing accurate affine invariant regions. In our framework, a method for extracting reliable seed points is first proposed. Then, regions which are invariant to most common affine transformations can be extracted from seed points by two new methods the Path Growing (PG) or the Thresholding Seeded Growing Region (TSGR). After that, an improved ellipse fitting method based on the Direct Least Square Fitting (DLSF) is used to fit the irregularly-shaped contours from the PG or the TSGR to obtain ellipse regions as the final invariant regions. In the experiments, our framework is first evaluated by the criterions of Mikolajczyk's evaluation framework [1], and then by near-duplicate detection problem [2]. Our framework shows its superiorities to the other detectors for different transformed images under Mikolajczyk's evaluation framework and the one with TSGR also gives satisfying results in the application to near-duplicate detection problem.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e90-d.11.1831/_p
Copy
@ARTICLE{e90-d_11_1831,
author={Li TIAN, Sei-ichiro KAMATA, },
journal={IEICE TRANSACTIONS on Information},
title={A New Framework for Constructing Accurate Affine Invariant Regions},
year={2007},
volume={E90-D},
number={11},
pages={1831-1840},
abstract={In this study, we propose a simple, yet general and powerful framework for constructing accurate affine invariant regions. In our framework, a method for extracting reliable seed points is first proposed. Then, regions which are invariant to most common affine transformations can be extracted from seed points by two new methods the Path Growing (PG) or the Thresholding Seeded Growing Region (TSGR). After that, an improved ellipse fitting method based on the Direct Least Square Fitting (DLSF) is used to fit the irregularly-shaped contours from the PG or the TSGR to obtain ellipse regions as the final invariant regions. In the experiments, our framework is first evaluated by the criterions of Mikolajczyk's evaluation framework [1], and then by near-duplicate detection problem [2]. Our framework shows its superiorities to the other detectors for different transformed images under Mikolajczyk's evaluation framework and the one with TSGR also gives satisfying results in the application to near-duplicate detection problem.},
keywords={},
doi={10.1093/ietisy/e90-d.11.1831},
ISSN={1745-1361},
month={November},}
Copy
TY - JOUR
TI - A New Framework for Constructing Accurate Affine Invariant Regions
T2 - IEICE TRANSACTIONS on Information
SP - 1831
EP - 1840
AU - Li TIAN
AU - Sei-ichiro KAMATA
PY - 2007
DO - 10.1093/ietisy/e90-d.11.1831
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E90-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2007
AB - In this study, we propose a simple, yet general and powerful framework for constructing accurate affine invariant regions. In our framework, a method for extracting reliable seed points is first proposed. Then, regions which are invariant to most common affine transformations can be extracted from seed points by two new methods the Path Growing (PG) or the Thresholding Seeded Growing Region (TSGR). After that, an improved ellipse fitting method based on the Direct Least Square Fitting (DLSF) is used to fit the irregularly-shaped contours from the PG or the TSGR to obtain ellipse regions as the final invariant regions. In the experiments, our framework is first evaluated by the criterions of Mikolajczyk's evaluation framework [1], and then by near-duplicate detection problem [2]. Our framework shows its superiorities to the other detectors for different transformed images under Mikolajczyk's evaluation framework and the one with TSGR also gives satisfying results in the application to near-duplicate detection problem.
ER -
English
