Detection of double JPEG compression plays an important role in digital image forensics. Some successful approaches have been proposed to detect double JPEG compression when the primary and secondary compressions have different quantization matrices. However, detecting double JPEG compression with the same quantization matrix is still a challenging problem. In this paper, an effective error-based statistical feature extraction scheme is presented to solve this problem. First, a given JPEG file is decompressed to form a reconstructed image. An error image is obtained by computing the differences between the inverse discrete cosine transform coefficients and pixel values in the reconstructed image. Two classes of blocks in the error image, namely, rounding error block and truncation error block, are analyzed. Then, a set of features is proposed to characterize the statistical differences of the error blocks between single and double JPEG compressions. Finally, the support vector machine classifier is employed to identify whether a given JPEG image is doubly compressed or not. Experimental results on three image databases with various quality factors have demonstrated that the proposed method can significantly outperform the state-of-the-art method.

An Effective Method for Detecting Double JPEG Compression With the Same Quantization Matrix

Detection of double Joint Photographic Experts Group (JPEG) compression is an important part of image forensics. Although methods in the past studies have been presented for detecting the double JPEG compression with a different quantization matrix, the detection of double JPEG compression with the same quantization matrix is still a challenging problem. In this paper, an effective method to detect the recompression in the color images by using the conversion error, rounding error, and truncation error on the pixel in the spherical coordinate system is proposed. The randomness of truncation errors, rounding errors, and quantization errors result in random conversion errors. The pixel number of the conversion error is used to extract six-dimensional features. Truncation error and rounding error on the pixel in its three channels are mapped to the spherical coordinate system based on the relation of a color image to the pixel values in the three channels. The former is converted into amplitude and angles to extract 30-dimensional features and 8-dimensional auxiliary features are extracted from the number of special points and special blocks. As a result, a total of 44-dimensional features have been used in the classification by using the support vector machine (SVM) method. Thereafter, the support vector machine recursive feature elimination (SVMRFE) method is used to improve the classification accuracy. The experimental results show that the performance of the proposed method is better than the existing methods.

Detecting Double JPEG Compressed Color Images With the Same Quantization Matrix in Spherical Coordinates

In order to extend the detection of JPEG compressed color images to solve the real-life problem, three-class classification forensics of JPEG compressed color images with the same quantization matrix is proposed. Since the previous methods treat detection of JPEG compressed color images as binary classification and JPEG compression with the same quantization matrix leaves slight tracks, three-class classification forensics of JPEG compressed color images with the same quantization matrix is a new and challenging problem. In this paper, two aspects are considered to solve this problem. First, if images are compressed, rounding and truncation error will occur. Thus, preprocessing of images is performed to extract error to highlight statistical difference which can help to classify. Second, the support vector machine (SVM) algorithm is originally designed for the binary classification problem, so dealing with a three-class problem, it is necessary to reconstruct a suitable three-class classifier. Besides, convolutional neural network (CNN) parallelly deal with three channels of the color image. The relationship of the three channels is terminated. However, quaternion convolutional neural network (QCNN) which utilizes quaternion algebra not only is directly used to three-class classification but also retain the relationship between three channels. Experimental results demonstrate that the proposed method achieves good performance and is better than the state-of-the-art approaches investigated.

/pdf/detection-of-triple-jpeg-compressed-color-images-12xt1ba5t4.pdf

Detection of Triple JPEG Compressed Color Images

With the development of digital image processing technique the credibility of digital image has been questioned. This paper proposes a new tamper detection method for clipped double JPEG compression image based on the statistical characteristics of DCT coefficients and block effect caused by double JPEG compression. The offset of the two DCT grids can be obtained by computing the loss of information. Then we will trim the image according to the offset, and it will be available to estimate the primary compression quality factor. The tampered area can be located according to the difference of DCT coefficients. Experiments results show that the proposed method is robust and effective in detecting the clipped double JPEG compression image. And the method is also applicable to the unclipped double JPEG compression image.

Tamper Detection Method for Clipped Double JPEG Compression Image

The detection of non-aligned double JPEG (NA-DJPEG) compression is one of the most important topics in the forensics of JPEG image. In this paper, we propose a novel feature set to detect NA-DJPEG compression based on refined intensity difference (RID), a new measure for blocking artifacts. Refined intensity difference is essentially intensity difference with compensation, which takes the negative effect of image texture into consideration when measuring blocking artifacts. The extraction pipeline of the proposed feature set mainly includes two steps. Firstly, two groups of RID histograms (totally sixteen histograms) with respect to horizontal and vertical directions are computed to describe the possible blocking artifacts in each row and column, and the bin values of these histograms are arranged to form an RID feature vector. Then, in order to make the RID feature vector less dependent on image texture and more discriminative, we calibrate it by a reference feature vector to generate a calibrated RID (C-RID) feature vector for final binary classification. Experiments have been conducted to validate the effectiveness of the C-RID feature set, and the results have shown that it outperforms the compared feature sets in most cases.

Detecting Non-aligned Double JPEG Compression Based on Refined Intensity Difference and Calibration

In this paper, we present an efficient method to locate the forged parts in a tampered JPEG image The forged region usually undergoes a different JPEG compression with the background region in JPEG image forgeries When a JPEG image is cropped to another host JPEG image and resaved in JPEG format, the JPEG block grid of the tampered region often mismatches the JPEG block grid of the host image with a certain shift This phenomenon is called non-aligned double JPEG compression (NA-DJPEG) In this paper, we identify different JPEG compression forms by estimating the shift of NA-DJPEG compression Our shift estimating approach is based on the percentage of non zeros of JPEG coefficients in different situations Compared to previous work, our tampering location method (i) performances better when dealing with small image size, (ii) is robust to common tampering processing such as resizing, rotating, blurring and so on, (iii) doesn't need an image dataset to train a machine learning based classifier or to get a proper threshold

/pdf/image-tampering-localization-via-estimating-the-non-aligned-54zbhhiqbq.pdf

Image tampering localization via estimating the non-aligned double JPEG compression

As an important branch of digital image forensics, image splicing is the most fundamental step in photomontage. In the present paper, an efficient blind digital forensics method for image splicing localization and forgery detection is proposed. The method is based on the estimated natural counterpart of the spliced image using different quality re-demosaicing approaches. By comparing the test image with its estimated natural counterpart, the abrupt edges along the spliced region are exposed and a binary image is obtained to illustrate the localization of the splicing. The features extracted from the binary image are fed into a support vector machine classifier to detect spliced forgeries. The DVMM uncompressed spliced image database is used to evaluate the performance of the proposed method. The experimental results show the effectiveness of the method on splicing localization and its accuracy on forgery detection.

/pdf/different-quality-re-demosaicing-in-digital-image-forensics-1t8p5a1c0q.pdf

Lanying Wu

Papers

Image tampering localization via estimating the non-aligned double JPEG compression

Different-quality Re-demosaicing in Digital Image Forensics