In this paper, a novel image zero-watermarking scheme against rotation attacks is proposed based on nonsubsampled pyramid decomposition (NSPD) and discrete cosine transform (DCT). It utilizes the intrinsic characteristics of NSPD and DCT to extract the robust feature of an image as the original zero-watermark. To increase the security of the proposed scheme, a variable parameter chaotic mapping (VPCM) is designed for the processes of watermark encryption and robust feature extraction. Firstly, the host gray-scale image is decomposed by NSPD, and the low-frequency sub-band image is divided into non-overlapping blocks. After the blocks are transformed by DCT, the signs of the first AC coefficients from all the blocks are used to construct a binary feature image. Then an exclusive-or operation is performed between the binary feature image and the encrypted watermark image to obtain the verification zero-watermark image. Furthermore, a method against arbitrary rotation attacks is employed to improve the robustness of the scheme against geometric attacks. The experimental results demonstrate that the proposed scheme is highly robust against various image processing attacks such as filtering, JPEG compression, scaling, translation, rotation and Checkmark attacks.

A new long-range-dependent (LRD) degradation model is described based on the generalized Cauchy (GC) process. The GC process is a two-parameter model, which describes local irregularities and global correlation characteristics of the data time sequence by the Hurst parameter $H$ and fractal dimension $D$ . Compared with the fractional Brownian motion (fBm) with linear relationship $H=2-D$ , two parameters of the GC process are independent of each other. The GC process is taken as the diffusion term to describe the LRD characteristics and uncertainty of the degradation process, and the degradation model is established in the form of power law and exponential drift. The Gaussian assumption of the GC process allows us to use linear system theory and statistics to derive its incremental distribution for obtaining the difference iteration form of the GC degradation model. Besides, the dimensionless factors, the principal component analysis (PCA), and the iterative method are used to eliminate the interference of noise on the degradation data. Then, the maximum prediction range of the GC degradation model in the degradation sequence is obtained by the reciprocal of the maximum Lyapunov exponent. Finally, the GC degradation model was applied for prediction of the remaining useful life (RUL) of rolling bearing. The validity of the GC degradation model is verified.

Median filtering (MF), a non-linear smoothing operation, has often been utilized as a means of image denoising to protect image edges and hide the traces of image tampering. Although the existing MF forensics methods have achieved excellent performance without post-processing, there is still a challenge of detecting MF in small image size and JPEG compression scenario. To meet this challenge, a robust MF forensic method using convolutional-neural-network (CNN)-based multiple residuals learning is proposed in this paper. Firstly, to reveal the traces left by MF, we use multiple high-pass filters to initialize the weights of the pre-processing layer, and obtain discriminatory residuals to characterize MF artifacts in various aspects. Then the output of the pre-processing layer is employed as the input of CNN, which is elaborately designed to extract rich hierarchical features for further classification. Furthermore, Batch Normalization (BN) is introduced as a regularization method to help accelerate convergence of the entire network. The extensive experimental results on the composite database demonstrate that the proposed method is superior to the state-of-the-art methods when detecting MF in both JPEG compressed and small size images.

A combination of spectral kurtosis (SK), based on Choi–Williams distribution (CWD) and hidden Markov models (HMM), accurately identifies initial gearbox failures and diagnoses fault types of gearboxes. First, using the LMD algorithm, five types of gearbox vibration signals are collected and decomposed into several product function (PF) components and the multicomponent signals are decomposed into single-component signals. Then, the kurtosis value of each component is calculated, and the component with the largest kurtosis value is selected for the CWD-SK analysis. According to the calculated CWD-SK value, the characteristics of the initial failure of the gearbox are extracted. This method not only avoids the difficulty of selecting the window function, but also provides original eigenvalues for fault feature classification. In the end, from the CWD-SK characteristic parameters at each characteristic frequency, the characteristic sequence based on CWD-SK is obtained with HMM training and diagnosis. The experimental results show that this method can effectively identify the initial fault characteristics of the gearbox, and also accurately classify the fault characteristics of different degrees.

Image copy-move forgery is a common simple tampering technique. To address issues such as high time complexity in most copy-move forgery detection algorithms and difficulty detecting forgeries in smooth regions, this paper proposes an image copy-move forgery detection algorithm based on fused features and density clustering. Firstly, the algorithm combines two detection methods, speeded up robust features (SURF) and accelerated KAZE (A-KAZE), to extract descriptive features by setting a low contrast threshold. Then, the density-based spatial clustering of applications with noise (DBSCAN) algorithm removes mismatched pairs and reduces false positives. To improve the accuracy of forgery localization, the algorithm uses the original image and the image transformed by the affine matrix to compare similarities in the same position in order to locate the forged region. The proposed method was tested on two datasets (Ardizzone and CoMoFoD). The experimental results show that the method effectively improved the accuracy of forgery detection in smooth regions, reduced computational complexity, and exhibited strong robustness against post-processing operations such as rotation, scaling, and noise addition.