Search

Frame duplication forgery is the most common inter-frame video forgery type to alter the contents of digital video sequences. It can be used for removing or duplicating some events within the same video sequences. Most of the existing frame duplication forgery detection methods fail to detect highly similar frames in the surveillance videos. In this paper, we propose a frame duplication forgery detection method based on textural feature analysis of video frames for digital video sequences. Firstly, we compute the single-level 2-D wavelet decomposition for each frame in the forged video sequences. Secondly, textural features of each frame are extracted using the Gray Level of the Co-Occurrence Matrix (GLCM). Four second-order statistical descriptors, Contrast, Correlation, Energy, and Homogeneity, are computed for the extracted textural features of GLCM. Furthermore, we calculate four statistical features from each frame (standard deviation, entropy, Root-Mean-Square RMS, and variance). Finally, the combination of GLCM's parameters and the other statistical features are then used to detect and localize the duplicated frames in the video sequences using the correlation between features. Experimental results demonstrate that the proposed approach outperforms other state-of-the-art (SOTA) methods in terms of P r e c i s i o n , R e c a l l , and F 1 S c o r e rates. Furthermore, the use of statistical features combined with GLCM features improves the performance of frame duplication forgery detection. [ABSTRACT FROM AUTHOR]

Infrared images have been widely used in many research areas, such as target detection and scene monitoring. Therefore, the copyright protection of infrared images is very important. In order to accomplish the goal of image-copyright protection, a large number of image-steganography algorithms have been studied in the last two decades. Most of the existing image-steganography algorithms hide information based on the prediction error of pixels. Consequently, reducing the prediction error of pixels is very important for steganography algorithms. In this paper, we propose a novel framework SSCNNP: a Convolutional Neural-Network Predictor (CNNP) based on Smooth-Wavelet Transform (SWT) and Squeeze-Excitation (SE) attention for infrared image prediction, which combines Convolutional Neural Network (CNN) with SWT. Firstly, the Super-Resolution Convolutional Neural Network (SRCNN) and SWT are used for preprocessing half of the input infrared image. Then, CNNP is applied to predict the other half of the infrared image. To improve the prediction accuracy of CNNP, an attention mechanism is added to the proposed model. The experimental results demonstrate that the proposed algorithm reduces the prediction error of the pixels due to full utilization of the features around the pixel in both the spatial and the frequency domain. Moreover, the proposed model does not require either expensive equipment or a large amount of storage space during the training process. Experimental results show that the proposed algorithm had good performances in terms of imperceptibility and watermarking capacity compared with advanced steganography algorithms. The proposed algorithm improved the PSNR by 0.17 on average with the same watermark capacity. [ABSTRACT FROM AUTHOR]

With high performances of image capturing tools, image information can be easily obtained by screenshots that make image copyright protection a challenging task. The existing screen-shooting watermarking algorithms suffer from a huge running time, in addition to their low robustness against different screenshot attacks, such as different distances and capturing angles of the screenshots. In this paper, a fast and robust high-capacity flexible watermarking algorithm for screenshot images is proposed. Firstly, Oriented FAST and Rotated BRIEF (ORB) feature points are extracted from the input image. Secondly, the feature points are then sorted in a descending order according to their response values. Then, the first five non-overlapping feature points are selected for the embedding by using Hamming window-based filtering method. Furthermore, we exploit the multi-resolution property of Discrete Wavelet Transform (DWT) and energy compaction property of Singular Value Decomposition (SVD) to embed the watermark. Therefore, the classical DWT combined with Singular Value Decomposition (SVD) are adopted to improve the robustness and capacity of the proposed watermarking algorithm. At the extraction side, the sum of the response values for the three RGB channels of the color-ripped image is calculated to improve the feature point localization accuracy. Experimental results show that the proposed screen-shooting watermarking algorithm improves running speed while ensuring the robustness. Furthermore, it has less time complexity and high robustness compared with the state-of-the-art watermarking algorithms against different screenshot attacks. [ABSTRACT FROM AUTHOR]

The hybridoma cell screening method is usually done manually by human eyes during the production process for monoclonal antibody drugs. This traditional screening method has certain limitations, such as low efficiency and subjectivity bias. Furthermore, most of the existing deep learning-based image segmentation methods have certain drawbacks, due to different shapes of hybridoma cells and uneven location distribution. In this paper, we propose a deep hybridoma cell image segmentation method based on residual and attention U-Net (RA-UNet). Firstly, the feature maps of the five modules in the network encoder are used for multi-scale feature fusion in a feature pyramid form and then spliced into the network decoder to enrich the semantic level of the feature maps in the decoder. Secondly, a dual attention mechanism module based on global and channel attention mechanisms is presented. The global attention mechanism (non-local neural network) is connected to the network decoder to expand the receptive field of the feature map and bring more rich information to the network. Then, the channel attention mechanism SENet (the squeeze-and-excitation network) is connected to the non-local attention mechanism. Consequently, the important features are enhanced by the learning of the feature channel weights, and the secondary features are suppressed, hence improving the cell segmentation performance and accuracy. Finally, the focal loss function is used to guide the network to learn the hard-to-classify cell categories. Furthermore, we evaluate the performance of the proposed RA-UNet method on a newly established hybridoma cell image dataset. Experimental results show that the proposed method has good reliability and improves the efficiency of hybridoma cell segmentation compared with state-of-the-art networks such as FCN, UNet, and UNet++. The results show that the proposed RA-UNet model has improvements of 0.8937%, 0.9926%, 0.9512%, and 0.9007% in terms of the dice coefficients, PA, MPA, and MIoU, respectively. [ABSTRACT FROM AUTHOR]

Deep learning has become an essential technique in image steganography. Most of the current deep-learning-based steganographic methods process digital images in the spatial domain. There are problems such as limited embedding capacity and unsatisfactory visual quality. To improve capacity-distortion performance, we develop a steganographic method from the frequency-domain perspective. We propose a module called the adaptive frequency-domain channel attention network (AFcaNet), which makes full use of the frequency features in each channel by a fine-grained manner of assigning weights. We apply this module to the state-of-the-art SteganoGAN, forming an Adaptive Frequency High-capacity Steganography Generative Adversarial Network (AFHS-GAN). The proposed neural network enhances the ability of high-dimensional feature extraction through overlaying densely connected convolutional blocks. In addition to this, a low-frequency loss function is introduced as an evaluation metric to guide the training of the network and thus reduces the modification of low-frequency regions of the image. Experimental results on the Div2K dataset show that our method has a better generalization capability compared to the SteganoGAN, with substantial improvement in both embedding capacity and stego-image quality. Furthermore, the embedding distribution of our method in the DCT domain is more similar to that of the traditional method, which is consistent with the prior knowledge of image steganography. [ABSTRACT FROM AUTHOR]

Mobile devices have been increasingly used to take pictures without leaving a trace. However, the application system can lead to confidential information leaks. A framework for screen-shooting-resilient watermarking via deep networks (SSDeN) in the frequency domain is put forward in this study to solve this problem. The proposed framework can extract the watermark from the leaked photo for copyright protection. SSDeN is an end-to-end process that combines convolutional neural network (CNN) with residual block to embed and extract watermarks in the DCT domain. We simulate some screen-shooting attacks to ensure the networks embed the watermark robustly. Our framework achieves the state-of-the-art performance on existing learning architectures for screen-shooting-resilient watermarking. [ABSTRACT FROM AUTHOR]

To protect the copyright of the color image, a color image watermarking scheme based on quaternion discrete Fourier transform (QDFT) and tensor decomposition (TD) is presented. Specifically, the cover image is partitioned into non-overlapping blocks, and then QDFT is performed on each image block. Then, the three imaginary frequency components of QDFT are used to construct a third-order tensor. The third-order tensor is decomposed by Tucker decomposition and generates a core tensor. Finally, an improved odd–even quantization technique is employed to embed a watermark in the core tensor. Moreover, pseudo-Zernike moments and multiple output least squares support vector regression (MLS–SVR) network model are used for geometric distortion correction in the watermark extraction stage. The scheme utilizes the inherent correlations among the three RGB channels of a color image, and spreads the watermark into the three channels. The experimental results indicate that the proposed scheme has better fidelity and stronger robustness for common image-processing and geometric attacks, can effectively resist each color channel exchange attack. Compared with the existing schemes, the presented scheme achieves better performance. [ABSTRACT FROM AUTHOR]

This paper proposes a screen-shooting resilient watermarking scheme via learned invariant keypoints and QT; that is, if the watermarked image is displayed on the screen and captured by a camera, the watermark can be still extracted from the photo. A screen-shooting resilient watermarking algorithm should meet the following two basic requirements: robust keypoints and a robust watermark algorithm. In our case, we embedded watermarks by combining the feature region filtering model to SuperPoint (FRFS) neural networks, quaternion discrete Fourier transform (QDFT), and tensor decomposition (TD). First we applied FRFS to locate the embedding feature regions which are decided by the keypoints that survive screen-shooting. Second, we structured watermark embedding regions centered at keypoints. Third, the watermarks were embedded by the QDFT and TD (QT) algorithm, which is robust for capturing process attacks. In a partial shooting scenario, the watermark is repeatedly embedded into different regions in an image to enhance robustness. Finally, we extracted the watermarks from at least one region at the extraction stage. The experimental results showed that the proposed scheme is very robust for camera shooting (including partial shooting) different shooting scenarios, and special attacks. Moreover, the efficient mechanism of screen-shooting resilient watermarking could have propietary protection and leak tracing applications. [ABSTRACT FROM AUTHOR]

Robust reversible watermarking in an encrypted domain is a technique that preserves privacy and protects copyright for multimedia transmission in the cloud. In general, most models of buildings and medical organs are constructed by three-dimensional (3D) models. A 3D model shared through the internet can be easily modified by an unauthorized user, and in order to protect the security of 3D models, a robust reversible 3D models watermarking method based on homomorphic encryption is necessary. In the proposed method, a 3D model is divided into non-overlapping patches, and the vertex in each patch is encrypted by using the Paillier cryptosystem. On the cloud side, in order to utilize addition and multiplication homomorphism of the Paillier cryptosystem, three direction values of each patch are computed for constructing the corresponding histogram, which is shifted to embed watermark. For obtaining watermarking robustness, the robust interval is designed in the process of histogram shifting. The watermark can be extracted from the symmetrical direction histogram, and the original encrypted model can be restored by histogram shifting. Moreover, the process of watermark embedding and extraction are symmetric. Experimental results show that compared with the existing watermarking methods in encrypted 3D models, the quality of the decrypted model is improved. Moreover, the proposed method is robust to common attacks, such as translation, scaling, and Gaussian noise. [ABSTRACT FROM AUTHOR]

Recently, more and more research has focused on the beautification technology of QR (Quick Response) codes. In this paper, a novel algorithm based on the XOR (exclusive OR) mechanism of hybrid basis vector matrices and a background image synthetic strategy is proposed. The hybrid basis vector matrices include the reverse basis vector matrix (RBVM) and positive basis vector matrix (PBVM). Firstly, the RBVM and PBVM are obtained by the Gauss–Jordan elimination method, according to the characteristics of the RS code. Secondly, the modification of the parity area of the QR code can be applied with the XOR operation of the RBVM, and the XOR operation of the PBVM is used to change the data area of the QR code. So, the QR code can be modified to be very close to the background image without impacting the error-correction ability. Finally, in order to further decrease the difference between the QR code and the background image, a new synthesis strategy is adopted in order to obtain a better aesthetic effect. The experimental results show that it obtains a better visual effect without the sacrificing recognition rate. [ABSTRACT FROM AUTHOR]

Blur is an important factor affecting the image quality. This paper presents an efficient no-reference (NR) image blur assessment method based on a response function of singular values. For an image, the grayscale image is computed to the acquire spatial information. In the meantime, the gradient map is computed to acquire the shape information, and the saliency map can be obtained by using scale-invariant feature transform (SIFT). Then, the grayscale image, the gradient map, and the saliency map are divided into blocks of the same size. The blocks of the gradient map are converted into discrete cosine transform (DCT) coefficients, from which the response function of singular values (RFSV) are generated. The sum of the RFSV are then utilized to characterize the image blur. The variance of the grayscale image and the DCT domain entropy of the gradient map are used to reduce the impact of the image content. The SIFT-dependent weights are calculated in the saliency map, which are assigned to the image blocks. Finally, the blur score is the normalized sum of the RFSV. Extensive experiments are conducted on four synthetic databases and two real blur databases. The experimental results indicate that the blur scores produced by our method are highly correlated with the subjective evaluations. Furthermore, the proposed method is superior to six state-of-the-art methods. [ABSTRACT FROM AUTHOR]