Local Multi-Coordinate System for Object Retrieval
Summary :
Encoding multiple SIFT descriptors into a single vector is a key technique for efficient object image retrieval. In this paper, we propose an extension of local coordinate system (LCS) for image representation. The previous LCS approaches encode each SIFT descriptor by a single local coordinate, which is not adequate for localizing its position in the descriptor space. Instead, we use multiple local coordinates to represent each descriptor with PCA-based decorrelation. Experiments show that this simple modification can improve retrieval performance significantly.
- Publication
- IEICE TRANSACTIONS on Information Vol.E99-D No.10 pp.2656-2660
- Publication Date
- 2016/10/01
- Publicized
- 2016/07/06
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2016EDL8109
- Type of Manuscript
- LETTER
- Category
- Image Processing and Video Processing
Authors
Go IRIE
NTT Corporation
Yukito WATANABE
NTT Corporation
Takayuki KUROZUMI
NTT Corporation
Tetsuya KINEBUCHI
NTT Corporation
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
Go IRIE, Yukito WATANABE, Takayuki KUROZUMI, Tetsuya KINEBUCHI, "Local Multi-Coordinate System for Object Retrieval" in IEICE TRANSACTIONS on Information,
vol. E99-D, no. 10, pp. 2656-2660, October 2016, doi: 10.1587/transinf.2016EDL8109.
Abstract: Encoding multiple SIFT descriptors into a single vector is a key technique for efficient object image retrieval. In this paper, we propose an extension of local coordinate system (LCS) for image representation. The previous LCS approaches encode each SIFT descriptor by a single local coordinate, which is not adequate for localizing its position in the descriptor space. Instead, we use multiple local coordinates to represent each descriptor with PCA-based decorrelation. Experiments show that this simple modification can improve retrieval performance significantly.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2016EDL8109/_p
Copy
@ARTICLE{e99-d_10_2656,
author={Go IRIE, Yukito WATANABE, Takayuki KUROZUMI, Tetsuya KINEBUCHI, },
journal={IEICE TRANSACTIONS on Information},
title={Local Multi-Coordinate System for Object Retrieval},
year={2016},
volume={E99-D},
number={10},
pages={2656-2660},
abstract={Encoding multiple SIFT descriptors into a single vector is a key technique for efficient object image retrieval. In this paper, we propose an extension of local coordinate system (LCS) for image representation. The previous LCS approaches encode each SIFT descriptor by a single local coordinate, which is not adequate for localizing its position in the descriptor space. Instead, we use multiple local coordinates to represent each descriptor with PCA-based decorrelation. Experiments show that this simple modification can improve retrieval performance significantly.},
keywords={},
doi={10.1587/transinf.2016EDL8109},
ISSN={1745-1361},
month={October},}
Copy
TY - JOUR
TI - Local Multi-Coordinate System for Object Retrieval
T2 - IEICE TRANSACTIONS on Information
SP - 2656
EP - 2660
AU - Go IRIE
AU - Yukito WATANABE
AU - Takayuki KUROZUMI
AU - Tetsuya KINEBUCHI
PY - 2016
DO - 10.1587/transinf.2016EDL8109
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E99-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2016
AB - Encoding multiple SIFT descriptors into a single vector is a key technique for efficient object image retrieval. In this paper, we propose an extension of local coordinate system (LCS) for image representation. The previous LCS approaches encode each SIFT descriptor by a single local coordinate, which is not adequate for localizing its position in the descriptor space. Instead, we use multiple local coordinates to represent each descriptor with PCA-based decorrelation. Experiments show that this simple modification can improve retrieval performance significantly.
ER -
English
