“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

Review: Digital image steganography: Survey and analysis of current methods

This chapter introduces the subject of statistical pattern recognition (SPR). It starts by considering how features are defined and emphasizes that the nearest neighbor algorithm achieves error rates comparable with those of an ideal Bayes’ classifier. The concepts of an optimal number of features, representativeness of the training data, and the need to avoid overfitting to the training data are stressed. The chapter shows that methods such as the support vector machine and artificial neural networks are subject to these same training limitations, although each has its advantages. For neural networks, the multilayer perceptron architecture and back-propagation algorithm are described. The chapter distinguishes between supervised and unsupervised learning, demonstrating the advantages of the latter and showing how methods such as clustering and principal components analysis fit into the SPR framework. The chapter also defines the receiver operating characteristic, which allows an optimum balance between false positives and false negatives to be achieved.

Statistical Pattern Recognition

In the past two decades, reversible data hiding (RDH), also referred to as lossless or invertible data hiding, has gradually become a very active research area in the field of data hiding. This has been verified by more and more papers on increasingly wide-spread subjects in the field of RDH research that have been published these days. In this paper, the various RDH algorithms and researches have been classified into the following six categories: 1) RDH into image spatial domain; 2) RDH into image compressed domain (e.g., JPEG); 3) RDH suitable for image semi-fragile authentication; 4) RDH with image contrast enhancement; 5) RDH into encrypted images, which is expected to have wide application in the cloud computation; and 6) RDH into video and into audio. For each of these six categories, the history of technical developments, the current state of the arts, and the possible future researches are presented and discussed. It is expected that the RDH technology and its applications in the real word will continue to move ahead.

Reversible Data Hiding: Advances in the Past Two Decades

In prediction-error expansion (PEE) based reversible data hiding, better exploiting image redundancy usually leads to a superior performance. However, the correlations among prediction-errors are not considered and utilized in current PEE based methods. Specifically, in PEE, the prediction-errors are modified individually in data embedding. In this paper, to better exploit these correlations, instead of utilizing prediction-errors individually, we propose to consider every two adjacent prediction-errors jointly to generate a sequence consisting of prediction-error pairs. Then, based on the sequence and the resulting 2D prediction-error histogram, a more efficient embedding strategy, namely, pairwise PEE, can be designed to achieve an improved performance. The superiority of our method is verified through extensive experiments.

Pairwise Prediction-Error Expansion for Efficient Reversible Data Hiding

As a retouching manipulation, contrast enhancement is typically used to adjust the global brightness and contrast of digital images. Malicious users may also perform contrast enhancement locally for creating a realistic composite image. As such it is significant to detect contrast enhancement blindly for verifying the originality and authenticity of the digital images. In this paper, we propose two novel algorithms to detect the contrast enhancement involved manipulations in digital images. First, we focus on the detection of global contrast enhancement applied to the previously JPEG-compressed images, which are widespread in real applications. The histogram peak/gap artifacts incurred by the JPEG compression and pixel value mappings are analyzed theoretically, and distinguished by identifying the zero-height gap fingerprints. Second, we propose to identify the composite image created by enforcing contrast adjustment on either one or both source regions. The positions of detected blockwise peak/gap bins are clustered for recognizing the contrast enhancement mappings applied to different source regions. The consistency between regional artifacts is checked for discovering the image forgeries and locating the composition boundary. Extensive experiments have verified the effectiveness and efficacy of the proposed techniques.

Contrast Enhancement-Based Forensics in Digital Images

A novel reversible data hiding scheme based on invariability of the sum of pixel pairs and pairwise difference adjustment (PDA) is presented in this letter. For each pixel pair, if a certain value is added to one pixel while the same value is subtracted from the other, then the sum of these two pixels will remain unchanged. How to properly select this value is the key issue for the balance between reversibility and distortion. In this letter, half the difference of a pixel pair plus 1-bit watermark has been elaborately selected to satisfy this purpose. In addition, PDA is proposed to significantly reduce the capacity consumed by overhead information. A series of experiments is conducted to verify the effectiveness and advantages of the proposed approach.

/pdf/reversible-watermarking-based-on-invariability-and-36mhbuwhyd.pdf

Reversible Watermarking Based on Invariability and Adjustment on Pixel Pairs

In digital image forensics, prior works are prone to the detection of malicious tampering. However, there is also a need for developing techniques to identify general content-preserved manipulations, which are employed to conceal tampering trails frequently. In this paper, we propose a blind forensic algorithm to detect median filtering (MF), which is applied extensively for signal denoising and digital image enhancement. The probability of zero values on the first order difference map in texture regions can serve as MF statistical fingerprint, which distinguishes MF from other operations. Since anti-forensic techniques enjoy utilizing MF to attack the linearity assumption of existing forensics algorithms, blind detection of the non-linear MF becomes especially significant. Both theoretically reasoning and experimental results verify the effectiveness of our proposed MF forensics scheme.

Forensic detection of median filtering in digital images

Recently, Li et al. proposed a reversible data hiding (RDH) method based on pixel-value-ordering (PVO) and prediction-error expansion. In their method, the maximum and the minimum of a pixel block are predicted and modified to embed data, and the reversibility is guaranteed by keeping PVO of each block invariant after embedding. In this paper, a novel RDH method is proposed by extending Li et al.@?s work. Instead of considering only a single pixel with maximum (or minimum) value of a block, all maximum-valued (or minimum-valued) pixels are taken as a unit to embed data. Specifically, the maximum-valued (or minimum-valued) pixels are first predicted and then modified together such that they are either unchanged or increased by 1 (or decreased by 1) in value at the same time. Comparing our method with Li et al.@?s, more blocks suitable for RDH are utilized and image redundancy is better exploited. Moreover, a mechanism of advisable payload partition and pixel-block-selection is adopted to optimize the embedding performance in terms of capacity-distortion behavior. Experimental results verify that our method outperforms Li et al.@?s and some other state-of-the-art works.

Rongrong Ni

Papers

Pairwise Prediction-Error Expansion for Efficient Reversible Data Hiding

Contrast Enhancement-Based Forensics in Digital Images

Reversible Watermarking Based on Invariability and Adjustment on Pixel Pairs

Forensic detection of median filtering in digital images

Reversible data hiding using invariant pixel-value-ordering and prediction-error expansion