Journal of Visual Communication and Image Representation最新文献

High-quality images are of prime importance for vision tasks in underwater environment, ocean exploitation and marine eco-environment protection. However, due to attenuation and scattering related to wavelength and distance, underwater images often suffer from severe distortion, like color cast and loss of detail, challenging the capture of high-quality images. Existing methods mostly focus on pixel-wise mapping from input to output images, which disrupts the latent relationships between neighboring pixels and suffers limited flexibility of linear mapping. Additionally, most methods operate solely within RGB color space, which is insensitive to some image properties such as luminance and saturation, may be inconsistent with human visual perception. In this paper, we combine global and local enhancement, formulating underwater image global enhancement as a task of image-specific piecewise curve estimation based on a deep network, introducing three color spaces (RGB, HSV, CIELab). Our network learns piecewise nonlinear curves specific to different channels of multiple color spaces, thereby introducing highly flexible nonlinear mapping and achieving targeted adjustment. Besides, we employ channel-wise attention mechanism to allocate weights for different adjustment results from multiple color spaces, combining their advantages to further enhance image properties such as luminance, saturation, and color, aiming to improve image quality and align it more closely with human visual perception. To assess the performance of the network, extensive experiments are conducted on synthetic and real-world underwater image datasets, with comparisons made against state-of-the-art methods. Both quantitative and qualitative results indicate our network’s remarkable performance in both visual quality and quantitative metrics.

The state of the art steganography approaches strictly assume that the receiver has access to a steganographic key. This limitation was mitigated for images in spacial domain, but the approach does not apply to JPEG images. In this paper, we introduce a keyless steganography scheme for JPEG images. Despite the spatial domain counterpart, our approach for the JPEG domain effectively preserves higher-order statistical models that are used in steganalysis. We show that our approach does not degrade image quality either. The proposed approach is a Side-Information (SI) steganography in the sense that its input is a never-compressed image. Another characteristic of the proposed approach is the separation of the embedding modification and data extraction domains, which can initiate further studies of similar approaches in the future.

With the rapid development of the Internet and multimedia technologies, multimedia applications integrating audio and video are becoming increasingly prevalent in both everyday life and professional environments. A critical challenge is to significantly enhance compression efficiency and bandwidth utilization while maintaining high-quality user experiences. To address this challenge, the Just Noticeable Distortion (JND) estimation model, which leverages the perceptual characteristics of the Human Visual System (HVS), is widely used in image and video coding for improved data compression. However, human visual perception is an integrative process that involves both visual and auditory stimuli. Therefore, this paper investigates the influence of audio signals on visual perception and presents a collaborative audio–video JND estimation model tailored for multimedia applications. Specifically, we characterize audio loudness, duration, and energy as temporal perceptual features, while assigning the audio saliency superimposed on the image plane as the spatial perceptual feature. An audio JND adjustment factor is then designed using a segmentation function. Finally, the proposed model combines the video-based JND model with the audio JND adjustment factor to form the audio–video collaborative JND estimation model. Compared with existing JND models, the model presented in this paper achieves the best subjective quality, with an average PSNR value of 26.97 dB. The experimental results confirm that audio significantly impacts human visual perception. The proposed audio–video collaborative JND model effectively enhances the accuracy of JND estimation for multimedia data, thereby improving compression efficiency and maintaining high-quality user experiences.

Low-light environments often lead to complex degradation of captured images. However, most deep learning-based image enhancement methods for low-light conditions only learn a single-channel mapping relationship between the input image in low-light conditions and the desired image in normal light without considering semantic priors. This may cause the network to deviate from the original color of the region. In addition, deep network architectures are not suitable for low-light image recovery due to low pixel values. To address these issues, we propose a novel network called SAGNet. It consists of two branches:the main branch extracts global enhancement features at the level of the original image, and the other branch introduces semantic information through region-based feature learning and learns local enhancement features for semantic regions with multi-level perception to maintain color consistency. The extracted features are merged with the global enhancement features for semantic consistency and visualization. We also propose an unsupervised loss function to improve the network’s adaptability to general scenes and reduce the effect of sparse datasets. Extensive experiments and ablation studies show that SAGNet maintains color accuracy better in all cases and keeps natural luminance consistency across the semantic range.

The existing deraining methods are based on convolutional neural networks (CNN) learning the mapping relationship between rainy and clean images. However, the real-valued CNN processes the color images as three independent channels separately, which fails to fully leverage color information. Additionally, sliding-window-based neural networks cannot effectively model the non-local characteristics of an image. In this work, we proposed a non-local feature aggregation quaternion network (NLAQNet), which is composed of two concurrent sub-networks: the Quaternion Local Detail Repair Network (QLDRNet) and the Multi-Level Feature Aggregation Network (MLFANet). Furthermore, in the subnetwork of QLDRNet, the Local Detail Repair Block (LDRB) is proposed to repair the backdrop of an image that has not been damaged by rain streaks. Finally, within the MLFANet subnetwork, we have introduced two specialized blocks, namely the Non-Local Feature Aggregation Block (NLAB) and the Feature Aggregation Block (Mix), specifically designed to address the restoration of rain-streak-damaged image backgrounds. Extensive experiments demonstrate that the proposed network delivers strong performance in both qualitative and quantitative evaluations on existing datasets. The code is available at https://github.com/xionggonghe/NLAQNet.

Most existing cross-modal retrieval methods face challenges in establishing semantic connections between different modalities due to inherent heterogeneity among them. To establish semantic connections between different modalities and align relevant semantic features across modalities, so as to fully capture important information within the same modality, this paper considers the superiority of hypergraph in representing higher-order relationships, and proposes an image-text retrieval method based on hypergraph clustering. Specifically, we construct hypergraphs to capture feature relationships within image and text modalities, as well as between image and text. This allows us to effectively model complex relationships between features of different modalities and explore the semantic connectivity within and across modalities. To compensate for potential semantic feature loss during the construction of the hypergraph neural network, we design a weight-adaptive coarse and fine-grained feature fusion module for semantic supplementation. Comprehensive experimental results on three common datasets demonstrate the effectiveness of the proposed method.

In the domain of computer vision, addressing the degradation of image quality under adverse weather conditions remains a significant challenge. To tackle the challenges of image enhancement and deraining in dark settings, we have integrated image enhancement and deraining technologies to develop the DDR (Dark Environment Deraining Network) system. This specialized network is designed to enhance and clarify images in low-light conditions compromised by raindrops. DDR employs a strategic divide-and-conquer approach and an apt network selection to discern patterns of raindrops and background elements within images. It is capable of mitigating noise and blurring induced by raindrops in dark settings, thus enhancing the visual fidelity of images. Through testing on real-world imagery and the Rain LOL dataset, this innovative network offers a robust solution for deraining tasks in dark conditions, inspiring advancements in the performance of computer vision systems under challenging weather scenarios. The research of DDR provides technical and theoretical support for improving image quality in dark environment.

Reversible data hiding in encrypted domain (RDH-ED) is widely used in sensitive fields such as privacy protection and copyright authentication. However, the embedding capacity of existing methods is generally low due to the insufficient use of model topology. In order to improve the embedding capacity, this paper proposes a high-capacity multi-MSB predictive reversible data hiding in encrypted domain (MMPRDH-ED). Firstly, the 3D model is subdivided by triangular mesh subdivision (TMS) algorithm, and its vertices are divided into reference set and embedded set. Then, in order to make full use of the redundant space of embedded vertices, Multi-MSB prediction (MMP) and Multi-layer Embedding Strategy (MLES) are used to improve the capacity. Finally, stream encryption technology is used to encrypt the model and data to ensure data security. The experimental results show that compared with the existing methods, the embedding capacity of MMPRDH-ED is increased by 53 %, which has higher advantages.

Facial Feature Point Detection (FFPD) plays a significant role in several face analysis tasks such as feature extraction and classification. This paper presents a Fully Automatic FFPD system using the application of Random Forest Regression Voting in a Constrained Local Model (RFRV-CLM) framework. A global detector is used to find the approximate positions of the facial region and eye centers. A sequence of local RFRV-CLMs are used to locate a detailed set of points around the facial features. Both global and local models use Random Forest Regression to vote for optimal positions. The system is evaluated in the task of facial expression localization using five different facial expression databases of different characteristics including age, intensity, 6-basic expressions, 22 compound expressions, static and dynamic images, and deliberate and spontaneous expressions. Quantitative results of the evaluation of automatic point localization against manual points (ground truth) demonstrated that the results of the proposed approach are encouraging and outperform the results of alternative techniques tested on the same databases.