Multi spatial resolution for image spam filtering

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Image spam filtering is a challenging task because spammers are constantly creating new tricks and making anti-spam filters ineffective. To overcome these problems, many new techniques have been developed. Most of these techniques use a basic bag-of-features representation where global approach is used to extract the feature. This global representation leads to limited descriptive power for the features due to neglecting the spatial information, which can create powerful cues for classification tasks. Spatial Pyramid Representation (SPR) is one of the most effective and widely used image processing techniques that embedding spatial information into a feature. Inspired by this technique, we propose Multi Spatial Resolution (MSR) approach, which transform the image to Base-64 encoding, divided the Base-64 encoding into a sequence of increasingly finer grids on different pyramid level. The n-gram technique is used to extract the features from each grid cell or partition. Frequency histogram for each partition is concatenated to form a single feature vector. The experiments were conducted on Dredze and SpamArchive data sets at four different resolutions using SVM classifier. The results show that MSR increased the classification performance compared to global approach.

Original languageEnglish
Title of host publicationLecture Notes in Electrical Engineering
PublisherSpringer Verlag
Pages1209-1217
Number of pages9
Volume362
ISBN (Print)9783319245829
DOIs
Publication statusPublished - 2016
Event2nd International Conference on Communication and Computer Engineering, ICOCOE 2015 - Phuket, Thailand
Duration: 9 Jun 201511 Jun 2015

Publication series

NameLecture Notes in Electrical Engineering
Volume362
ISSN (Print)18761100
ISSN (Electronic)18761119

Other

Other2nd International Conference on Communication and Computer Engineering, ICOCOE 2015
CountryThailand
CityPhuket
Period9/6/1511/6/15

Fingerprint

Image processing
Classifiers
Experiments

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering

Cite this

Ariff, N. A. M., Abdullah, A., & Nasrudin, M. F. (2016). Multi spatial resolution for image spam filtering. In Lecture Notes in Electrical Engineering (Vol. 362, pp. 1209-1217). (Lecture Notes in Electrical Engineering; Vol. 362). Springer Verlag. https://doi.org/10.1007/978-3-319-24584-3_103

Multi spatial resolution for image spam filtering. / Ariff, Nor Azman Mat; Abdullah, Azizi; Nasrudin, Mohammad Faidzul.

Lecture Notes in Electrical Engineering. Vol. 362 Springer Verlag, 2016. p. 1209-1217 (Lecture Notes in Electrical Engineering; Vol. 362).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ariff, NAM, Abdullah, A & Nasrudin, MF 2016, Multi spatial resolution for image spam filtering. in Lecture Notes in Electrical Engineering. vol. 362, Lecture Notes in Electrical Engineering, vol. 362, Springer Verlag, pp. 1209-1217, 2nd International Conference on Communication and Computer Engineering, ICOCOE 2015, Phuket, Thailand, 9/6/15. https://doi.org/10.1007/978-3-319-24584-3_103
Ariff NAM, Abdullah A, Nasrudin MF. Multi spatial resolution for image spam filtering. In Lecture Notes in Electrical Engineering. Vol. 362. Springer Verlag. 2016. p. 1209-1217. (Lecture Notes in Electrical Engineering). https://doi.org/10.1007/978-3-319-24584-3_103
Ariff, Nor Azman Mat ; Abdullah, Azizi ; Nasrudin, Mohammad Faidzul. / Multi spatial resolution for image spam filtering. Lecture Notes in Electrical Engineering. Vol. 362 Springer Verlag, 2016. pp. 1209-1217 (Lecture Notes in Electrical Engineering).
@inproceedings{1f3a8b0f433e40488d6a2b3006fde1ae,
title = "Multi spatial resolution for image spam filtering",
abstract = "Image spam filtering is a challenging task because spammers are constantly creating new tricks and making anti-spam filters ineffective. To overcome these problems, many new techniques have been developed. Most of these techniques use a basic bag-of-features representation where global approach is used to extract the feature. This global representation leads to limited descriptive power for the features due to neglecting the spatial information, which can create powerful cues for classification tasks. Spatial Pyramid Representation (SPR) is one of the most effective and widely used image processing techniques that embedding spatial information into a feature. Inspired by this technique, we propose Multi Spatial Resolution (MSR) approach, which transform the image to Base-64 encoding, divided the Base-64 encoding into a sequence of increasingly finer grids on different pyramid level. The n-gram technique is used to extract the features from each grid cell or partition. Frequency histogram for each partition is concatenated to form a single feature vector. The experiments were conducted on Dredze and SpamArchive data sets at four different resolutions using SVM classifier. The results show that MSR increased the classification performance compared to global approach.",
author = "Ariff, {Nor Azman Mat} and Azizi Abdullah and Nasrudin, {Mohammad Faidzul}",
year = "2016",
doi = "10.1007/978-3-319-24584-3_103",
language = "English",
isbn = "9783319245829",
volume = "362",
series = "Lecture Notes in Electrical Engineering",
publisher = "Springer Verlag",
pages = "1209--1217",
booktitle = "Lecture Notes in Electrical Engineering",

}

TY - GEN

T1 - Multi spatial resolution for image spam filtering

AU - Ariff, Nor Azman Mat

AU - Abdullah, Azizi

AU - Nasrudin, Mohammad Faidzul

PY - 2016

Y1 - 2016

N2 - Image spam filtering is a challenging task because spammers are constantly creating new tricks and making anti-spam filters ineffective. To overcome these problems, many new techniques have been developed. Most of these techniques use a basic bag-of-features representation where global approach is used to extract the feature. This global representation leads to limited descriptive power for the features due to neglecting the spatial information, which can create powerful cues for classification tasks. Spatial Pyramid Representation (SPR) is one of the most effective and widely used image processing techniques that embedding spatial information into a feature. Inspired by this technique, we propose Multi Spatial Resolution (MSR) approach, which transform the image to Base-64 encoding, divided the Base-64 encoding into a sequence of increasingly finer grids on different pyramid level. The n-gram technique is used to extract the features from each grid cell or partition. Frequency histogram for each partition is concatenated to form a single feature vector. The experiments were conducted on Dredze and SpamArchive data sets at four different resolutions using SVM classifier. The results show that MSR increased the classification performance compared to global approach.

AB - Image spam filtering is a challenging task because spammers are constantly creating new tricks and making anti-spam filters ineffective. To overcome these problems, many new techniques have been developed. Most of these techniques use a basic bag-of-features representation where global approach is used to extract the feature. This global representation leads to limited descriptive power for the features due to neglecting the spatial information, which can create powerful cues for classification tasks. Spatial Pyramid Representation (SPR) is one of the most effective and widely used image processing techniques that embedding spatial information into a feature. Inspired by this technique, we propose Multi Spatial Resolution (MSR) approach, which transform the image to Base-64 encoding, divided the Base-64 encoding into a sequence of increasingly finer grids on different pyramid level. The n-gram technique is used to extract the features from each grid cell or partition. Frequency histogram for each partition is concatenated to form a single feature vector. The experiments were conducted on Dredze and SpamArchive data sets at four different resolutions using SVM classifier. The results show that MSR increased the classification performance compared to global approach.

UR - http://www.scopus.com/inward/record.url?scp=84955453264&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84955453264&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-24584-3_103

DO - 10.1007/978-3-319-24584-3_103

M3 - Conference contribution

SN - 9783319245829

VL - 362

T3 - Lecture Notes in Electrical Engineering

SP - 1209

EP - 1217

BT - Lecture Notes in Electrical Engineering

PB - Springer Verlag

ER -