Median filtering (MF) is frequently applied to conceal the traces of forgery and therefore can provide indirect forensic evidence of tampering when investigating composite images. The existing MF forensic methods, however, ignore how JPEG compression affects median filtered images, resulting in heavy performance degradation when detecting filtered images stored in the JPEG format. In this paper, we propose a new robust MF forensic method based on a modified convolutional neural network (CNN). First, relying on the analysis of the influence on median filtered images caused by JPEG compression, we effectively suppress the interference using image deblocking. Second, the fingerprints left by MF are highlighted via filtered residual fusion. These two functions are fulfilled with a deblocking layer and a fused filtered residual (FFR) layer. Finally, the output of the FFR layer becomes input when extracting multiple features for further classification using a tailor-made CNN. The extensive experimental results show that the proposed method outperforms the state-of-the-art methods in both JPEG compressed and small-sized MF image detection. INDEX TERMS Median filtering, convolutional neural networks, robust forensics, JPEG compression, image deblocking.
This paper compares holographic and traditional digital image watermarking by a watermarking algorithm in DWT domain, in which the four sub images of 1-scale wavelet transformed watermark image are embedded into the four corresponding images of 2-scales wavelet transformed host image respectively. By this watermarking algorithm, test results show that the hidden images of holographic watermarking survive geometric distortion more than the traditional one, especially cropping, and the Gaussian filter, Gaussian noise and JPEG compress resilient properties of traditional watermarking are a little better than the holographic watermarking.
In order to reconstruct a surface by using the data from RGB-D sensor, this paper presents a viewpoint based method for estimating the orientation of point clouds. Firstly, a PCA method is used to compute the normal vector of each point. In this process, the orientation of the normal is determined by the viewpoint. Secondly, the point clouds generated from each frame are combined to an overall model with directional information. Finally, the quality of the model is further improved by a local smooth method. The experimental results show that the method can compute accurate normal vectors on the fly. Compared to current methods, it can estimate the sign of the normal automatically.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.