Application of scale invariant feature transform to image spam filter

Junwei Chen; Lichun Zhang; Yue Lu

doi:10.1109/FGCNS.2008.24

Application of scale invariant feature transform to image spam filter

Junwei Chen^*
, Lichun Zhang
, Yue Lu

^*Corresponding author for this work

School of Communication and Electronic Engineering

East China Normal University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Scopus citations

Abstract

Inspired by the keyword-based text filter, this paper proposes an image filter which detects the spam image by matching with user-specified image content. In this way, detecting image spam e-mail is converted into image matching process. Stable local feature detection and representation is a fundamental component of image matching algorithms. SIFT has been proven to be the most robust local invariant feature descriptor. In this process, SIFT algorithm is applied. The images are extracted with SIFT features, which are used to carry out the image matching work. Our experiments demonstrate that SIFT has a good performance in spam image recognition.

Original language	English
Title of host publication	Proceedings - 2008 2nd International Conference on Future Generation Communication and Networking Symposia, FGCN 2008
Pages	55-58
Number of pages	4
DOIs	https://doi.org/10.1109/FGCNS.2008.24
State	Published - 2008
Event	2008 2nd International Conference on Future Generation Communication and Networking Symposia, FGCN 2008 - Hainan, China Duration: 13 Dec 2008 → 15 Dec 2008

Publication series

Name	Proceedings of the 2008 2nd International Conference on Future Generation Communication and Networking, FGCN 2008
Volume	3

Conference

Conference	2008 2nd International Conference on Future Generation Communication and Networking Symposia, FGCN 2008
Country/Territory	China
City	Hainan
Period	13/12/08 → 15/12/08

Access to Document

10.1109/FGCNS.2008.24

Cite this

Chen, J., Zhang, L., & Lu, Y. (2008). Application of scale invariant feature transform to image spam filter. In Proceedings - 2008 2nd International Conference on Future Generation Communication and Networking Symposia, FGCN 2008 (pp. 55-58). Article 4813547 (Proceedings of the 2008 2nd International Conference on Future Generation Communication and Networking, FGCN 2008; Vol. 3). https://doi.org/10.1109/FGCNS.2008.24

@inproceedings{d7d8f28f057b43399979e1fc074a0a1c,

title = "Application of scale invariant feature transform to image spam filter",

abstract = "Inspired by the keyword-based text filter, this paper proposes an image filter which detects the spam image by matching with user-specified image content. In this way, detecting image spam e-mail is converted into image matching process. Stable local feature detection and representation is a fundamental component of image matching algorithms. SIFT has been proven to be the most robust local invariant feature descriptor. In this process, SIFT algorithm is applied. The images are extracted with SIFT features, which are used to carry out the image matching work. Our experiments demonstrate that SIFT has a good performance in spam image recognition.",

author = "Junwei Chen and Lichun Zhang and Yue Lu",

year = "2008",

doi = "10.1109/FGCNS.2008.24",

language = "英语",

isbn = "9780769535463",

series = "Proceedings of the 2008 2nd International Conference on Future Generation Communication and Networking, FGCN 2008",

pages = "55--58",

booktitle = "Proceedings - 2008 2nd International Conference on Future Generation Communication and Networking Symposia, FGCN 2008",

note = "2008 2nd International Conference on Future Generation Communication and Networking Symposia, FGCN 2008 ; Conference date: 13-12-2008 Through 15-12-2008",

}

Chen, J, Zhang, L & Lu, Y 2008, Application of scale invariant feature transform to image spam filter. in Proceedings - 2008 2nd International Conference on Future Generation Communication and Networking Symposia, FGCN 2008., 4813547, Proceedings of the 2008 2nd International Conference on Future Generation Communication and Networking, FGCN 2008, vol. 3, pp. 55-58, 2008 2nd International Conference on Future Generation Communication and Networking Symposia, FGCN 2008, Hainan, China, 13/12/08. https://doi.org/10.1109/FGCNS.2008.24

Application of scale invariant feature transform to image spam filter. / Chen, Junwei; Zhang, Lichun; Lu, Yue.
Proceedings - 2008 2nd International Conference on Future Generation Communication and Networking Symposia, FGCN 2008. 2008. p. 55-58 4813547 (Proceedings of the 2008 2nd International Conference on Future Generation Communication and Networking, FGCN 2008; Vol. 3).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Application of scale invariant feature transform to image spam filter

AU - Chen, Junwei

AU - Zhang, Lichun

AU - Lu, Yue

PY - 2008

Y1 - 2008

N2 - Inspired by the keyword-based text filter, this paper proposes an image filter which detects the spam image by matching with user-specified image content. In this way, detecting image spam e-mail is converted into image matching process. Stable local feature detection and representation is a fundamental component of image matching algorithms. SIFT has been proven to be the most robust local invariant feature descriptor. In this process, SIFT algorithm is applied. The images are extracted with SIFT features, which are used to carry out the image matching work. Our experiments demonstrate that SIFT has a good performance in spam image recognition.

AB - Inspired by the keyword-based text filter, this paper proposes an image filter which detects the spam image by matching with user-specified image content. In this way, detecting image spam e-mail is converted into image matching process. Stable local feature detection and representation is a fundamental component of image matching algorithms. SIFT has been proven to be the most robust local invariant feature descriptor. In this process, SIFT algorithm is applied. The images are extracted with SIFT features, which are used to carry out the image matching work. Our experiments demonstrate that SIFT has a good performance in spam image recognition.

UR - https://www.scopus.com/pages/publications/67650266471

U2 - 10.1109/FGCNS.2008.24

DO - 10.1109/FGCNS.2008.24

M3 - 会议稿件

AN - SCOPUS:67650266471

SN - 9780769535463

T3 - Proceedings of the 2008 2nd International Conference on Future Generation Communication and Networking, FGCN 2008

SP - 55

EP - 58

BT - Proceedings - 2008 2nd International Conference on Future Generation Communication and Networking Symposia, FGCN 2008

T2 - 2008 2nd International Conference on Future Generation Communication and Networking Symposia, FGCN 2008

Y2 - 13 December 2008 through 15 December 2008

ER -

Chen J, Zhang L, Lu Y. Application of scale invariant feature transform to image spam filter. In Proceedings - 2008 2nd International Conference on Future Generation Communication and Networking Symposia, FGCN 2008. 2008. p. 55-58. 4813547. (Proceedings of the 2008 2nd International Conference on Future Generation Communication and Networking, FGCN 2008). doi: 10.1109/FGCNS.2008.24

Application of scale invariant feature transform to image spam filter

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this