Normalized energy density-based forensic detection of resampled images

Xiaoying Feng; Ingemar J Cox; Gwenaël Doërr

Normalized energy density-based forensic detection of resampled images

Xiaoying Feng, Ingemar J Cox, Gwenaël Doërr

79 Citationer (Scopus)

Abstract

We propose a new method to detect resampled imagery. The method is based on examining the normalized energy density present within windows of varying size in the second derivative of the image in the frequency domain, and exploiting this characteristic to derive a 19-D feature vector that is used to train a SVM classifier. Experimental results are reported on 7500 raw images from the BOSS database. Comparison with prior work reveals that the proposed algorithm performs similarly for resampling rates greater than 1, and is superior to prior work for resampling rates less than 1. Experiments are performed for both bilinear and bicubic interpolations, and qualitatively similar results are observed for each. Results are also provided for the detection of resampled imagery with noise corruption and JPEG compression. As expected, some degradation in performance is observed as the noise increases or the JPEG quality factor declines.

Originalsprog	Udefineret/Ukendt
Tidsskrift	Multimedia, IEEE Transactions on
Vol/bind	14
Udgave nummer	3
Sider (fra-til)	536-545
Antal sider	10
Status	Udgivet - 2012
Udgivet eksternt	Ja

Citationsformater

@article{e72c1991eb164da08e6979e41bda4068,

title = "Normalized energy density-based forensic detection of resampled images",

abstract = "We propose a new method to detect resampled imagery. The method is based on examining the normalized energy density present within windows of varying size in the second derivative of the image in the frequency domain, and exploiting this characteristic to derive a 19-D feature vector that is used to train a SVM classifier. Experimental results are reported on 7500 raw images from the BOSS database. Comparison with prior work reveals that the proposed algorithm performs similarly for resampling rates greater than 1, and is superior to prior work for resampling rates less than 1. Experiments are performed for both bilinear and bicubic interpolations, and qualitatively similar results are observed for each. Results are also provided for the detection of resampled imagery with noise corruption and JPEG compression. As expected, some degradation in performance is observed as the noise increases or the JPEG quality factor declines.",

author = "Xiaoying Feng and Cox, {Ingemar J} and Gwena{\"e}l Do{\"e}rr",

year = "2012",

language = "Udefineret/Ukendt",

volume = "14",

pages = "536--545",

journal = "Multimedia, IEEE Transactions on",

publisher = "IEEE",

number = "3",

}

TY - JOUR

T1 - Normalized energy density-based forensic detection of resampled images

AU - Feng, Xiaoying

AU - Cox, Ingemar J

AU - Doërr, Gwenaël

PY - 2012

Y1 - 2012

N2 - We propose a new method to detect resampled imagery. The method is based on examining the normalized energy density present within windows of varying size in the second derivative of the image in the frequency domain, and exploiting this characteristic to derive a 19-D feature vector that is used to train a SVM classifier. Experimental results are reported on 7500 raw images from the BOSS database. Comparison with prior work reveals that the proposed algorithm performs similarly for resampling rates greater than 1, and is superior to prior work for resampling rates less than 1. Experiments are performed for both bilinear and bicubic interpolations, and qualitatively similar results are observed for each. Results are also provided for the detection of resampled imagery with noise corruption and JPEG compression. As expected, some degradation in performance is observed as the noise increases or the JPEG quality factor declines.

AB - We propose a new method to detect resampled imagery. The method is based on examining the normalized energy density present within windows of varying size in the second derivative of the image in the frequency domain, and exploiting this characteristic to derive a 19-D feature vector that is used to train a SVM classifier. Experimental results are reported on 7500 raw images from the BOSS database. Comparison with prior work reveals that the proposed algorithm performs similarly for resampling rates greater than 1, and is superior to prior work for resampling rates less than 1. Experiments are performed for both bilinear and bicubic interpolations, and qualitatively similar results are observed for each. Results are also provided for the detection of resampled imagery with noise corruption and JPEG compression. As expected, some degradation in performance is observed as the noise increases or the JPEG quality factor declines.

M3 - Tidsskriftartikel

VL - 14

SP - 536

EP - 545

JO - Multimedia, IEEE Transactions on

JF - Multimedia, IEEE Transactions on

IS - 3

ER -