S-SIFT: A shorter SIFT without least discriminability visual orientation

Sheng Hua Zhong; Yan Liu; Gangshan Wu

doi:10.1109/WI-IAT.2012.134

S-SIFT: A shorter SIFT without least discriminability visual orientation

Sheng Hua Zhong
, Yan Liu
, Gangshan Wu

The Hong Kong Polytechnic University

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

5 Citations (Scopus)

Abstract

Detection and description of local features are a classical problem in image processing and multimedia content analysis. Based on the in homogeneity of visual orientation in human visual system, we propose a novel algorithm S-SIFT to detect and describe local image features. In three stages of S-SIFT, the information from the least discriminability orientation is omitting. Compared with the standard SIFT algorithm, S-SIFT has lower dimension and provides a faster key point matching. Experiments on the standard dataset demonstrate that our algorithm yields comparable or even better results for feature detection and matching tasks.

Original language	English
Title of host publication	Proceedings - 2012 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2012
Pages	669-672
Number of pages	4
DOIs	https://doi.org/10.1109/WI-IAT.2012.134
Publication status	Published - 1 Dec 2012
Event	2012 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2012 - Macau, China Duration: 4 Dec 2012 → 7 Dec 2012

Conference

Conference	2012 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2012
Country/Territory	China
City	Macau
Period	4/12/12 → 7/12/12

Keywords

descriptors
real-world distribution
scale-invariant feature transform
visual orientation

ASJC Scopus subject areas

Artificial Intelligence
Software

More information

10.1109/WI-IAT.2012.134

Cite this

@inproceedings{fb2105e04545463a9626e11e6e1e9f55,

title = "S-SIFT: A shorter SIFT without least discriminability visual orientation",

abstract = "Detection and description of local features are a classical problem in image processing and multimedia content analysis. Based on the in homogeneity of visual orientation in human visual system, we propose a novel algorithm S-SIFT to detect and describe local image features. In three stages of S-SIFT, the information from the least discriminability orientation is omitting. Compared with the standard SIFT algorithm, S-SIFT has lower dimension and provides a faster key point matching. Experiments on the standard dataset demonstrate that our algorithm yields comparable or even better results for feature detection and matching tasks.",

keywords = "descriptors, real-world distribution, scale-invariant feature transform, visual orientation",

author = "Zhong, \{Sheng Hua\} and Yan Liu and Gangshan Wu",

year = "2012",

month = dec,

day = "1",

doi = "10.1109/WI-IAT.2012.134",

language = "English",

isbn = "9780769548807",

pages = "669--672",

booktitle = "Proceedings - 2012 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2012",

note = "2012 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2012 ; Conference date: 04-12-2012 Through 07-12-2012",

}

S-SIFT: A shorter SIFT without least discriminability visual orientation. / Zhong, Sheng Hua; Liu, Yan; Wu, Gangshan.
Proceedings - 2012 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2012. 2012. p. 669-672 6511960.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - S-SIFT: A shorter SIFT without least discriminability visual orientation

AU - Zhong, Sheng Hua

AU - Liu, Yan

AU - Wu, Gangshan

PY - 2012/12/1

Y1 - 2012/12/1

N2 - Detection and description of local features are a classical problem in image processing and multimedia content analysis. Based on the in homogeneity of visual orientation in human visual system, we propose a novel algorithm S-SIFT to detect and describe local image features. In three stages of S-SIFT, the information from the least discriminability orientation is omitting. Compared with the standard SIFT algorithm, S-SIFT has lower dimension and provides a faster key point matching. Experiments on the standard dataset demonstrate that our algorithm yields comparable or even better results for feature detection and matching tasks.

AB - Detection and description of local features are a classical problem in image processing and multimedia content analysis. Based on the in homogeneity of visual orientation in human visual system, we propose a novel algorithm S-SIFT to detect and describe local image features. In three stages of S-SIFT, the information from the least discriminability orientation is omitting. Compared with the standard SIFT algorithm, S-SIFT has lower dimension and provides a faster key point matching. Experiments on the standard dataset demonstrate that our algorithm yields comparable or even better results for feature detection and matching tasks.

KW - descriptors

KW - real-world distribution

KW - scale-invariant feature transform

KW - visual orientation

UR - https://www.scopus.com/pages/publications/84878437018

U2 - 10.1109/WI-IAT.2012.134

DO - 10.1109/WI-IAT.2012.134

M3 - Conference article published in proceeding or book

SN - 9780769548807

SP - 669

EP - 672

BT - Proceedings - 2012 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2012

T2 - 2012 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2012

Y2 - 4 December 2012 through 7 December 2012

ER -

S-SIFT: A shorter SIFT without least discriminability visual orientation

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this