Blind detection of median filtering using linear and nonlinear descriptors

Abstract

Recently, for the recovery of images' processing history, passive forensics of possible manipulations has attracted wide interest. In particular, due to highly non-linearity, median filtering (MF) usually serves as an effective tool of counter forensic techniques for other image operations. Therefore, the importance of median filtering detection is selfevident. In this paper, through analysing the pixel differences of images, we found the indications to study the complex correlations introduced by median filtering and adopt two sets of describing features to measure them. More Specifically, we utilize a linear prediction model for the differences of image that is computed along a specific direction and estimate the prediction coefficients to construct a linear descriptor L. Besides, we make use of the histogram of rotation invariant local binary pattern (LBP) to form a nonlinear descriptor N . According to our observation, we also propose an enhanced feature EF to further improve the detection performance. Based on these, we present a novel median filtering detection scheme incorporating both the linear and nonlinear descriptors. Extensive experiments are carried out, which demonstrate that our proposed scheme gains favorable performance comparing to state-of-the-art methods, especially for low resolution images and JPEG compressed images, and shows resistance to noise attack.

SPAM revisited for median filtering detection using higher‐order difference

“…In most of the MF detection techniques , initially, the FOD is calculated in different directions followed by features extraction. Although these methods provide good results for high‐resolution and low‐compressed images, yet their results degrade for the blurred and highly compressed low‐resolution images.…”

“…Most of the MF detection methods use the support vector machine (SVM) with Gaussian or radial basis function (RBF) kernel for classification. In this paper, we use the Linear Discriminant Analysis (LDA) classifier, which is extensively used in supervised learning as well as for dimension reduction.…”

“…Several methods for MF detection have been discussed . Kircher and Fridrich utilize the first‐order difference (FOD) for detecting MF in an image, naming the resultant image as FOD image.…”

“…It applies autoregressive model on the median filter residual for computing autoregressive coefficients, which are used as features for median filter detection. The researchers in discuss linear and nonlinear descriptors. The linear descriptor estimates the features (prediction coefficients) from the FOD image in different directions and the nonlinear descriptor uses the rotation‐invariant local binary pattern.…”

Medical Image Blind Integrity Verification with Krawtchouk Moments

“…These techniques do not require any additional image information besides the image itself to detect whether it has been modified or not [ 9 ]. Many blind forensics methods have been proposed for the detection of various modifications of natural images including noise addition [ 10 ], median filtering [ 11 ], copy-move modification [ 12 , 13 ], JPEG compression [ 14 ]. Notice that blind forensics techniques can also be used for image steganalysis purpose, that is, to detect whether an image has been modified so as to dissimulate a secret message in between spies [ 15 – 18 ].…”