Signal Processing-Image Communication最新文献

With the growing development and wide clinical application of CT technology, the potential radiation damage to patients has sparked public concern. However, reducing the radiation dose may cause large amounts of noise and artifacts in the reconstructed images, which may affect the accuracy of the clinical diagnosis. Therefore, improving the quality of low-dose CT scans has become a popular research topic. Generative adversarial networks (GAN) have provided new research ideas for low-dose CT (LDCT) denoising. However, utilizing only image decomposition or adding new functional subnetworks cannot effectively fuse the same type of features with different scales (or different types of features). Thus, most current GAN-based denoising networks often suffer from low feature utilization and increased network complexity. To address these problems, we propose a coarse-to-fine multiscale feature hybrid low-dose CT denoising network (CMFHGAN). The generator consists of a global denoising module, local texture feature enhancement module, and self-calibration feature fusion module. The three modules complement each other and guarantee overall denoising performance. In addition, to further improve the denoising performance, we propose a multi-resolution inception discriminator with multiscale feature extraction ability. Experiments were performed on the Mayo and Piglet datasets, and the results showed that the proposed method outperformed the state-of-the-art denoising algorithms.

This article proposes the “RGB Pixel N-grams” descriptor, which uses a sequence of $n$ pixels to represent RGB color texture images. We conducted classification experiments with three different classifiers and five color texture image databases to evaluate the descriptor’s performance, using accuracy as the evaluation metric. These databases include various textures from different surfaces, sometimes under different lighting, scale, or rotation conditions. The proposed descriptor proved to be robust and competitive compared to other state-of-the-art descriptors, as it has better accuracy in classification results in most databases and classifiers.

While recent research on salient object detection (SOD) has shown remarkable progress in leveraging both RGB and depth data, it is still worth exploring how to use the inherent relationship between the two to extract and fuse features more effectively, and further make more accurate predictions. In this paper, we consider combining the attention mechanism with the characteristics of the SOD, proposing the Dual Attention Guided Multi-scale Fusion Network. We design the multi-scale fusion block by combining multi-scale branches with channel attention to achieve better fusion of RGB and depth information. Using the characteristic of the SOD, the dual attention module is proposed to make the network pay more attention to the currently unpredicted saliency regions and the wrong parts in the already predicted regions. We perform an ablation study to verify the effectiveness of each component. Quantitative and qualitative experimental results demonstrate that our method achieves state-of-the-art (SOTA) performance.

Under poor illumination, the image information captured by a camera is partially lost, which seriously affects the visual perception of the human. Inspired by the idea that the fusion of multiexposure images can yield one high-quality image, an adaptive enhancement framework for a single low-light image is proposed based on the strategy of virtual exposure. In this framework, the exposure control parameters are adaptively generated through a statistical analysis of the low-light image, and a virtual exposure enhancer constructed by a quadratic function is applied to generate several image frames from a single input image. Then, on the basis of generating weight maps by three factors, i.e., contrast, saturation and saliency, the image sequences and weight images are transformed by a Laplacian pyramid and Gaussian pyramid, respectively, and multiscale fusion is implemented layer by layer. Finally, the enhanced result is obtained by pyramid reconstruction rule. Compared with the experimental results of several state-of-the-art methods on five datasets, the proposed method shows its superiority on several image quality evaluation metrics. This method requires neither image calibration nor camera response function estimation and has a more flexible application range. It can weaken the possibility of overenhancement, effectively avoid the appearance of a halo in the enhancement results, and adaptively improve the visual information fidelity.

Interframe EZBC/JP2K has been shown to be an effective fine-grain scalable video coding system. However, its Lagrange multiplier values for motion estimation of multiple temporal levels are not specified, and must be specified by the user in the config file in order to run the program. In this paper, we investigate how to select these Lagrange parameters for optimized performance. By designing an iterative mechanism, we make it possible for the encoder to adaptively select Lagrange multipliers based on the feedback of Y-PSNR closed GOP performance. Experimental results regarding both classic test video clips and their concatenations are obtained and discussed. We also present a new analytical model for optimized Lagrange multiplier selection in terms of target Y-PSNR.

Although numerous methods have been proposed to remove blocking artifacts in JPEG-compressed images, one important issue not well addressed so far is the construction of a unified model that requires no prior knowledge of the JPEG encoding parameters to operate effectively on different compression-level images (grayscale/color) while occupying relatively small storage space to save and run. To address this issue, in this paper, we present a unified JPEG compression artifact reduction model called DSPW-Net, which employs (1) the deep steerable pyramid wavelet transform network for Y-channel restoration, and (2) the classic U-Net architecture for CbCr-channel restoration. To enable our model to work effectively on images with a wide range of compression levels, the quality factor (QF) related features extracted by the convolutional layers in the QF-estimation network are incorporated in the two restoration branches. Meanwhile, recursive blocks with shared parameters are utilized to drastically reduce model parameters and shared-source residual learning is employed to avoid the gradient vanishing/explosion problem in training. Extensive quantitative and qualitative results tested on various benchmark datasets demonstrate the effectiveness of our model as compared with other state-of-the-art deblocking methods.

Augmented reality applications are beginning to change the way sports are broadcast, providing richer experiences and valuable insights to fans. The first step of augmented reality systems is camera calibration, possibly based on detecting the line markings of the playing field. Most existing proposals for line detection rely on edge detection and Hough transform, but radial distortion and extraneous edges cause inaccurate or spurious detections of line markings. We propose a novel strategy to automatically and accurately segment and classify line markings. First, line points are segmented thanks to a stochastic watershed transform that is robust to radial distortions, since it makes no assumptions about line straightness, and is unaffected by the presence of players or the ball. The line points are then linked to primitive structures (straight lines and ellipses) thanks to a very efficient procedure that makes no assumptions about the number of primitives that appear in each image. The strategy has been tested on a new and public database composed by 60 annotated images from matches in five stadiums. The results obtained have proven that the proposed strategy is more robust and accurate than existing approaches, achieving successful line mark detection even under challenging conditions.

The explosive growth of video data constitutes a series of new challenges in computer vision, and the function of video summarization (VS) is becoming more and more prominent. Recent works have shown the effectiveness of sparse dictionary selection (SDS) based VS, which selects a representative frame set to sufficiently reconstruct a given video. Existing SDS based VS methods use conventional handcrafted features or single-scale deep features, which could diminish their summarization performance due to the underutilization of frame feature representation. Deep learning techniques based on convolutional neural networks (CNNs) exhibit powerful capabilities among various vision tasks, as the CNN provides excellent feature representation. Therefore, in this paper, a multi-scale deep feature fusion based sparse dictionary selection (MSDFF-SDS) is proposed for VS. Specifically, multi-scale features include the directly extracted features from the last fully connected layer and the global average pooling (GAP) processed features from intermediate layers, then VS is formulated as a problem of minimizing the reconstruction error using the multi-scale deep feature fusion. In our formulation, the contribution of each scale of features can be adjusted by a balance parameter, and the row-sparsity consistency of the simultaneous reconstruction coefficient is used to select as few keyframes as possible. The resulting MSDFF-SDS model is solved by using an efficient greedy pursuit algorithm. Experimental results on two benchmark datasets demonstrate that the proposed MSDFF-SDS improves the F-score of keyframe based summarization more than 3% compared with the existing SDS methods, and performs better than most deep-learning methods for skimming based summarization.

Just noticeable distortion (JND), reflecting the perceptual redundancy directly, has been widely used in image and video compression. However, the human visual system (HVS) is extremely complex and the visual signal processing has not been fully understood, which result in existing JND models are not accurate enough and the bitrate saving of JND-based perceptual compression schemes is limited. This paper presents a novel pixel-based JND model for videos and a JND-based perceptual quantization scheme for HEVC codecs. In particular, positive and negative perception effects of the inter-frame difference and the motion information are analyzed and measured with an information-theoretic approach. Then, a surprise-based JND model is developed for perceptual video coding (PVC). In our PVC scheme, the frame-level perceptual quantization parameter (QP) is derived on the premise that the coding distortion is infinitely close to the estimated JND threshold. On the basis of the frame-level perceptual QP, we determine the perceptual QP for each coding unit through a perceptual adjustment function to achieve better perceptual quality. Experimental results indicate that the proposed JND model outperforms existing models significantly, the proposed perceptual quantization scheme improves video compression efficiency with better perceptual quality and lower coding complexity.

Image steganography aims to achieve covert communication between two partners utilizing stego images generated by hiding secret images within cover images. Existing deep image steganography methods have been rapidly developed in this area. Such methods, however, usually generate the stego images and reveal the secret images using one-process networks, lacking sufficient refinement in these methods. Thus, the security and quality of stego and revealed secret images still have much room for promotion, especially for large-capacity image steganography. This paper proposes Joint Adjustment Image Steganography Networks (JAIS-Nets), containing a series of coarse-to-fine iterative adjustment processes, for image steganography. Our JAIS-Nets first proposes Cross-Process Contrastive Refinement (CPCR) adjustment method, using the cross-process contrastive information from cover-stego and secret-revealed secret image pairs, to iteratively refine the generated stego and revealed secret images, respectively. In addition, our JAIS-Nets further proposes Cross-Process Multi-Scale (CPMS) adjustment method, using the cross-process multi-scale information from different scales cover-stego and secret-revealed secret image pairs, to directly adjust and enhance the intermediate representations of the proposed JAIS-Nets. Integrating the proposed CPCR with CPMS methods, the proposed JAIS-Nets can jointly adjust the quality of the stego and revealed secret images at both the learning process and image scale levels. Extensive experiments demonstrate that our JAIS-Nets can achieve state-of-the-art performances on the security and quality of the stego and revealed secret images on both the regular and large capacity image steganography.