Sight Research Articles

On the Links Between Exposure to Traumatic Events in Religious Contexts, Post-Traumatic Stress Symptoms, and a Positive Perception of God's Image Among Jewish Lesbians, Gays and Bisexuals in Israel.

This study constitutes one of the first investigations aiming to examine the association between traumatic experiences within religious settings and symptoms of post-traumatic stress among religious lesbians, gays, and bisexuals. Furthermore, the study tested whether the anticipated positive link between those traumatic experiences and post-traumtic stress is influenced by a positive perception of God's image. The sample consisted of 146 Israeli Jewish lesbians, gays, and bisexuals who professed a belief in God or demonstrated religious inclinations either presently or in the past. They completed self-report measures via an online questionnaire, assessing traumatic experiences within religious settings, post-traumtic stress symptoms, and positive perceptions of God's image. The findings revealed a significant and robust positive connection between traumatic experiences within religious settings and post-traumtic stress. A positive perception of God's image exhibited a negative correlation with post-traumtic stress but did not moderate the relationship traumatic experiences within religious settings and symptoms of post-traumatic stress. These findings highlight the significance of traumatic experiences within religious settings as a distinct potential risk factor of post-traumtic stress among lesbians, gays, and bisexuals and underscore the necessity of enhancing awareness among mental health professionals, religious leaders, and legal entities regarding the detrimental effects of those expereinces.

포스트 시네마 환경에서의 관객 현전에 관한 연구

This study defines the diversified media environment of contemporary visual art as a post-cinema environment and analyzes how the spatial expansion of the screen and the conceptual transformation of the camera have occurred within it. By examining the altered methods of image production, mediation, and reception, the research reveals the presence of the spectator as a noncorporeal subject in the visual field of image experience. The changes in the screen and the audience have been driven by the transition to multi-screen and multimedia environments, leading to a transformation in visual perception through physical environments that interact with images in expanded spaces. Additionally, the post-cinema camera, as a non-human agency, has broadened the scope of image production and mediation through computer imaging processes and digital technologies. It not only intervenes between the unexperienced realities beyond human cognition and the audience as the experiencing subject, but also produces and mediates images for machines as machine vision, facilitating the process of converting representation into information. Furthermore, this study argues that the issue of spectator presence in the visual field can be understood through the paradox of absence and presence in the technological context of 21st-century media. It asserts that the spectator emerges as an “electronic body” that transcends the physical body in the image reception environment. The concept of the audience's electronic body introduces perspectives on the coding and informatization of the body due to technological interventions by computers and media, as well as the hybrid sensations resulting from the interaction between bodies and devices, proposing a new notion of corporeality for non-corporeal subjects in the new media environment.

Employee suicide: The effect of cause, employer response, and gender on perceptions of organisational brand image and support.

Employee suicide: The effect of cause, employer response, and gender on perceptions of organisational brand image and support.

Jewelry of Eastern Lanna Identity: Strategies and Approaches for Contemporary Jewelry Design from Cultural Identity

Today’s jewelry designs look more contemporary, emphasizing self-expression by reflecting the perspectives and ideas of designers and artists in the context of society, culture, ethnicity, aesthetics, technology and ways of life through designs that are unique and in line with today’s lifestyles to create new artistic approaches. This research presents strategies and guidelines for designing contemporary jewelry from cultural capital by using the eastern Lanna area as a case study. The researchers conducted a unique analysis by studying the image and identity of the provinces in the eastern Lanna region, which led to the development of strategies and guidelines for jewelry design that reflect the eastern Lanna identity, as well as assessment of the perceptions of and satisfaction with jewelry prototypes designed by these strategies and such guidelines. The results showed that, in this research, the BLEND strategy was used in contemporary jewelry design, which was developed from the interpretation of the identity, image and characteristics of the provinces in the eastern Lanna group, into a design development in the form of a mixed design, or hybridization. These guidelines for creative design have generated design terms and conditions to present the value of work that expresses identity through four elements, namely 1) color, 2) materials, 3) patterns/shapes, and 4) story contents, which are synthesized through the perception of representative images to design and produce jewelry prototypes. The results of the evaluation of the jewelry prototypes as a whole revealed that the jewelry can express the eastern Lanna identity in an effective way, resulting in the creation of new knowledge in design, which is the development of concepts and processes to interpret new meanings in design in order to create value and worth as part of the utilization of cultural capital in the development of the country.

Enhancing Underwater SLAM Navigation and Perception: A Comprehensive Review of Deep Learning Integration

Underwater simultaneous localization and mapping (SLAM) is essential for effectively navigating and mapping underwater environments; however, traditional SLAM systems have limitations due to restricted vision and the constantly changing conditions of the underwater environment. This study thoroughly examined the underwater SLAM technology, particularly emphasizing the incorporation of deep learning methods to improve performance. We analyzed the advancements made in underwater SLAM algorithms. We explored the principles behind SLAM and deep learning techniques, examining how these methods tackle the specific difficulties encountered in underwater environments. The main contributions of this work are a thorough assessment of the research into the use of deep learning in underwater image processing and perception and a comparison study of standard and deep learning-based SLAM systems. This paper emphasizes specific deep learning techniques, including generative adversarial networks (GANs), convolutional neural networks (CNNs), long short-term memory (LSTM) networks, and other advanced methods to enhance feature extraction, data fusion, scene understanding, etc. This study highlights the potential of deep learning in overcoming the constraints of traditional underwater SLAM methods, providing fresh opportunities for exploration and industrial use.

Combining visual cues with relaxing music, perfume and ventilation to reduce passenger car sickness: An experimental study

The autonomous, digital, and electric transformation of passenger vehicles is projected to elevate the incidence of motion sickness among occupants. This study investigates the effectiveness of an “anti-motion sickness” system that features dynamic light stimuli to support visual perception of longitudinal motion, combined with relaxing music, perfume and ventilation pulses to enhance user wellbeing. In an experimental design aimed at replicating a realistic passenger drive, fifty-three subjects were tested as front passengers engaged in a gaming activity. Subjective motion sickness ratings were collected throughout the drive, and the development of symptoms was monitored through in-ear physiological measurements, including RR-intervals, core temperature, and oxygen saturation. Post hoc analyses indicated non-significant improvement in subjective assessments of motion sickness. Similarly, physiological measurements did not demonstrate any significant difference across conditions. The tested system was however more effective in mitigating car sickness for low susceptible than for mid-to-high susceptible individuals.

Evaluating the general V(λ), mismatch spectral quality factor index ƒ₁ and the uncertainty of photometers

The general term photometry refers to the measurement of light and its perceived brightness; it can be applied to various purposes, including lighting design, display calibration, and the setting of safety standards. A device used for measuring light is called a light meter or photometer. Ideally, such devices should have a spectral responsivity-that is, they should respond to light in a way which mimics the human eye's sensitivity to different wavelengths. The sensitivity of the human eye is described by the Commission Internationale de l'Éclairage, CIE, luminous efficiency function, V(λ), a plot of the sensitivity of the eye versus wavelength over the visible region, from violet, approximately 380 nm, through red, approximately 780 nm. In practical applications, it is usually preferable to detect light with silicon or selenium photodetectors and measure the electrical current generated. These photodetectors are sensitive to a wide range of wavelengths, including those outside of the visible spectrum: ultraviolet (UV) and infrared (IR). However, due to its nature, the spectral responsivity of silicon and selenium photodetectors is also different from that of the human eye. For example, silicon photodetectors are much more sensitive to infrared radiation, which is imperceptible to human vision. This in turn leads to erroneous light measurements when using the direct raw response of the detector. The spectral quality factor and , indicating the mismatch between the spectral responsivity and the CIE luminous efficiency function V(λ), is the most crucial characteristic of photometers. The general mismatch index , denoted as V(λ), delineates the disparity between a photometer's relative spectral responsivity and the spectral luminous efficiency function for photopic vision, V(λ). It's highly probable that photometers will adopt white light-emitting diode (LED) sources as calibration references going forward. This transition may necessitate refining the general V(λ) mismatch index's definition, possibly through alternative normalization methods for or by introducing a different assessment function for evaluating mismatches . In this research, spectral quality factor for the photometer NIS-2 has been determined with value 3.8%. This percentage value is classified the photometer NIS-2 as medium quality. The uncertainty was determined through a calculation performed using my Microsoft Excel program, and the final value obtained is 0.010.

The influence of neighbor selection on self-organized UAV swarm based on finite perception vision.

Recently, vision-based unmanned aerial vehicle (UAV) swarming has emerged as a promising alternative that can overcome the adaptability and scalability limitations of distributed and communication-based UAV swarm systems. While most vision-based control algorithms are predicated on the detection of neighboring objects, they often overlook key perceptual factors such as visual occlusion and the impact of visual sensor limitations on swarm performance. To address the interaction problem of neighbor selection at the core of self-organizing UAV swarm control, a perceptually realistic finite perception visual (FPV) neighbor selection model is proposed, which is based on the lateral visual characteristics of birds, incorporates adjustable lateral visual field widths and orientations, and is able to ignore occluded agents. Based on the FPV model, a neighbor selection method based on the Acute Angle Test (AAT) is proposed,
which overcomes the limitation that the traditional neighbor selection mechanism can only interact with the nearest neighboring agents. A large number of Monte Carlo simulation comparison experiments show that the proposed FPV+AAT neighborselection mechanism can reduce the redundant communication burden between large scale self-organized UAV swarms, and outperforms the traditional neighbor selection method in terms of order, safety, union, connectivity, and noise resistance.

Dual-path aggregation transformer network for super-resolution with images occlusions and variability

While Transformer-based approaches have recently achieved notable success in super-resolution, their extensive computational requirements impede widespread practical adoption. High-resolution meteorological satellite cloud imagery is essential for weather analysis and forecasting. Enhancing image resolution through super-resolution techniques facilitates the accurate identification and localization of geographic features by meteorological systems. However, current super-resolution methods fail to restore the intricacies of cloud formations and complex regions fully. This research introduces a novel dual-path aggregation Transformer network (DPAT) tailored to enhance the super-resolution of meteorological satellite cloud images. The DPAT network adeptly captures cloud imagery's subtle details and textures, effectively addressing occlusions and the variability inherent in satellite imagery. It bolsters the model's ability to manage the complex attributes of cloud images through the introduction of the Dual-path Aggregation Self-Attention (DASA) mechanism and the Multi-scale Feature Aggregation Block (MFAB), thereby enhancing performance in processing intricate cloud features. The DASA mechanism synthesizes features across spatial, depth, and channel dimensions via a dual-path approach, thoroughly exploiting feature correlations. The MFAB, designed to supplant the multilayer perceptron, incorporates shift convolution and a multi-scale interaction block to augment feature information, compensating for the deficiency in local information absorption due to fixed receptive fields. Experimental outcomes indicate that DPAT delivers superior super-resolution outcomes. With a parameter count of only 32% of the Enhanced Deep Residual Network (EDSR) or 77% of the Image Restoration using Shift Window Transformer (SwinIR), DPAT matches SwinIR's performance on the satellite cloud dataset. Moreover, DPAT balances accuracy and parameter economy across various datasets. This technology is expected to improve image super-resolution capabilities in multiple fields such as human action recognition and industrial recognition, and indirectly improve the accuracy of image perception tasks.

Multi-modal scene graph inspired policy for visual navigation

Visual navigation needs the agent locate the given target with visual perception. To enable robots to effectively execute tasks, combining large language models (LLMs) with multi-modal inputs in navigation is necessary. While LLMs offer rich semantic knowledge, they lack specific real-world information and real-time interaction capabilities. This paper introduces a Multi-modal Scene Graph (MMSG) navigation framework that aligns LLMs with visual perception models to predict next steps. Firstly, a multi-modal scene dataset is constructed, containing triplets of object-relations-target words. We provide target words and lists of existing objects in the scene to generate a large number of instructions and corresponding action plans for GPT-\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$-$$\\end{document}3.5. The generated data is then utilized for pre-train LLM for path planning. During inference, we discover objects in the scene by extending the DETR visual object detector to multi-view RGB image collected from different reachable positions. Experimental results show that path planning generated from MMSG outperforms state-of-the-art methods, indicating its feasibility in complex environments. We evaluate our methods on the ProTHOR dataset and show superior navigation performance.

Human Vision as A Multi-Circuit Mathematical Model of the Automated Control System

Abstract The paper contains a proposal an original, extended mathematical model of an automatic system of human vision reaction to a forcing light pulse. A comprehensive mathematical model of the vision process was proposed in the form of an equation described in the frequency (dynamics) domain. Mathematical modelling of human senses is very important. It enables better integration of automation systems with a human cooperating with them, also as an automation system. This provides the basis for reasoning based on a mathematical model instead of intuitive reasoning about human reactions to visual stimuli. A block diagram of the proposed system with five human reaction paths is given. The following can be distinguished in the scheme: the main track consisting of: the transport delay of the eye reaction, the transport delay of the afferent nerves, the inertia of the brain with a preemptive action, the transport delay of the centrifugal nerves and the inertial and transport delay of the neuromotor system. In addition, the scheme of the system includes four tracks of negative feedback of motor and force reactions: upper eyelid, lower eyelid, pupil and lens. In the proposed model, the components of each path along with their partial mathematical models are given and discussed. For each reaction path, their overall mathematical models are also given. Taking into account the comprehensive models of all five reaction paths, a complete mathematical model of the automatic system of human reaction to a forcing light impulse is proposed. The proposed mathematical model opens up many possibilities for synchronizing it with mathematical models of many mechatronics and automation systems and their research. Optimizing the parameters of this model and its synchronization with specific models of automation systems is difficult and requires many numerical experiments. This approach enables the design of automation systems that are better synchronized with human reactions to existing stimuli and the selection of optimal parameters of their operation already in the design phase. The proposed model allows, for example, accurate determination of difficulty levels in computer games. Another example of the use of the proposed model is the study of human reactions to various situations generated virtually, for example in flight simulators and other similar ones.

INTENSITAS PENGGUNAAN MEDIA SOSIAL DAN PERSEPSI REMAJA TENTANG CITRA TUBUH IDEAL

The intensity of social media (Instagram) usage is how long and how often someone accesses it. The duration of accessing Instagram often triggers perceptions about ideal body image in society. The purpose of this study to analyze the effect of the intensity of Instagram social media usage on adolescents' perceptions about ideal body image at SMA Negeri 4 Purwokerto. The research method used is a non-experimental quantitative research type with a cross-sectional approach. The sample consisted of 124 students. The research instruments included a questionnaire that measured the intensity of Instagram usage using a scale adapted from previous researchers and the perception of ideal body image using the Multidimensional Body Self-Relations Questionnaire (MBSRQ) measuring instrument. The test results using SPSS version 25, the characteristics of the respondents were mostly female (72.6%), the intensity of Instagram usage and adolescents' perceptions about body image were in the moderate category, 73.4% and 60.5%, respectively. The results of the Spearman rank test showed a p value of 0.004 (<0.05) so that H1 was accepted and H2 was rejected. Thus, there is an influence between the intensity of Instagram use and ideal body image with a significance value of 0.004 <0.05, so it can be concluded that the two variables are correlated with a correlation coefficient value of 0.259, which means that the level of relationship between the two variables is in a very weak relationship.

Immersive remote telerobotics: foveated unicasting and remote visualization for intuitive interaction

Abstract Precise and efficient performance in remote robotic teleoperation relies on intuitive interaction. This requires both accurate control actions and complete perception (vision, haptic, and other sensory feedback) of the remote environment. Especially in immersive remote teleoperation, the complete perception of remote environments in 3D allows operators to gain improved situational awareness. Color and Depth (RGB-D) cameras capture remote environments as dense 3D point clouds for real-time visualization. However, providing enough situational awareness needs fast, high-quality data transmission from acquisition to virtual reality rendering. Unfortunately, dense point-cloud data can suffer from network delays and limits, impacting the teleoperator’s situational awareness. Understanding how the human eye works can help mitigate these challenges. This paper introduces a solution by implementing foveation, mimicking the human eye’s focus by smartly sampling and rendering dense point clouds for an intuitive remote teleoperation interface. This provides high resolution in the user’s central field, which gradually reduces toward the edges. However, this systematic visualization approach in the peripheral vision may benefit or risk losing information and burdening the user’s cognitive load. This work investigates these advantages and drawbacks through an experimental study and describes the overall system, with its software, hardware, and communication framework. This will show significant enhancements in both latency and throughput, surpassing 60% and 40% improvements in both aspects when compared with state-of-the-art research works. A user study reveals that the framework has minimal impact on the user’s visual quality of experience while helping to reduce the error rate significantly. Further, a 50% reduction in task execution time highlights the benefits of the proposed framework in immersive remote telerobotics applications.

Assessing the influence of visual stimulus properties on steady-state visually evoked potentials and pupil diameter

Steady-State Visual Evoked Potentials (SSVEPs) are brain responses measurable via electroencephalography (EEG) in response to continuous visual stimulation at a constant frequency. SSVEPs have been instrumental in advancing our understanding of human vision and attention, as well as in the development of brain-computer interfaces (BCIs). Ongoing questions remain about which type of visual stimulus causes the most potent SSVEP response. The current study investigated the effects of color, size, and flicker frequency on the signal-to-noise ratio of SSVEPs, complemented by pupillary light reflex measurements obtained through an eye-tracker. Six participants were presented with visual stimuli that differed in terms of color (white, red, green), shape (circles, squares, triangles), size (10,000 to 30,000 pixels), flicker frequency (8 to 25 Hz), and grouping (one stimulus at a time versus four stimuli presented in a 2×2 matrix to simulate a BCI). The results indicated that larger stimuli elicited stronger SSVEP responses and more pronounced pupil constriction. Additionally, the results revealed an interaction between stimulus color and flicker frequency, with red being more effective at lower frequencies and white at higher frequencies. Future SSVEP research could focus on the recommended waveform, interactions between SSVEP and power grid frequency, a wider range of flicker frequencies, a larger sample of participants, and a systematic comparison of the information transfer obtained through SSVEPs, pupil diameter, and eye movements.

A Knowledge Base Driven Task-Oriented Image Semantic Communication Scheme

With the development of artificial intelligence and computer hardware, semantic communication has been attracting great interest. As an emerging communication paradigm, semantic communication can reduce the requirement for channel bandwidth by extracting semantic information. This is an effective method that can be applied to image acquisition of unmanned aerial vehicles, which can transmit high-data-volume images within the constraints of limited available bandwidth. However, the existing semantic communication schemes fail to adequately incorporate the guidance of task requirements into the semantic communication process and are difficult to adapt to the dynamic changes of tasks. A task-oriented image semantic communication scheme driven by knowledge base is proposed, aiming at achieving high compression ratio and high quality image reconstruction, and effectively solving the bandwidth limitation. This scheme segments the input image into several semantic information unit under the guidance of task requirements by Yolo-World and Segment Anything Model. The assigned bandwidth for each unit is according to the task relevance scores, which enables high-quality transmission of task-related information with lower communication overheads. An improved metric weighted learned perceptual image patch similarity (LPIPS) is proposed to evaluate the transmission accuracy of the novel scheme. Experimental results show that our scheme achieves a notable performance improvement on weighted LPIPS while the same compression ratio compared with traditional image compression schemes. Our scheme has a higher target capture ratio than traditional image compression schemes under the task of target detection.

Time to consider ruling out inclusion bodies denaturing protocols for spontaneous solubilization of biologically active proteins

The formation of inclusion bodies (IBs) in microbial cell factories is a very common process occurring during recombinant protein production. Different protocols have been developed for the extraction of soluble proteins from IBs using several strategies, ranging from the use of harsh denaturing and high concentrations of chaotropic agents and reducing agents to the use of mild protocols based on the use of non-denaturing detergents. However, in recent years, the biological vision of IBs has changed and research studies have demonstrated that these protein aggregates contain biologically active and properly folded recombinant proteins. This drives us to redefine the methodologies currently used to obtain soluble protein using IB as a protein source. Hence, we propose the extraction of IB protein via the simple spontaneous solubilization of IB as a strategy broadly applicable to all kinds of recombinant proteins without the negative effects of detergents and chaotropic agents on final biological activity. We prove the wide applicability of spontaneous solubilization processes to different types of IBs and that protocols can be easily customized for each protein in terms of timing and incubation temperature by monitoring the protein activity of the solubilized fraction.

Reflections of Self: How Social Media Shapes Teen Body Image

This research explores how advances in information technology, particularly through social media, have transformed communication patterns and influenced teenagers' body image perceptions. Employing a qualitative approach, the study conducted in-depth interviews with three teenage girls aged 17-21 who are active on social media. The findings indicate that many participants experience dissatisfaction with their bodies due to comparisons with prevalent beauty standards. This aligns with social comparison theory, which suggests that individuals often evaluate their appearance by contrasting themselves with others. Social interactions on social media, including comments and likes, also play a significant role in shaping self-confidence. While the pressure to conform to unrealistic beauty ideals is a notable negative effect, some participants reported feeling motivated to pursue healthier lifestyles as a positive outcome. The study highlights the need for effective interventions aimed at educating adolescents about healthy social media use and raising awareness of its potential effects on body image.

Subclinical variability in visual function modulates visual dependence - independent of age

AbstractParadoxically visual dependence is reported to increase with age, contributing to falls risk, whereas visual function typically declines. This study assesses the relationship between age, objective and subjective measures of visual function and visual dependence, in healthy young and older adults. Forty-four healthy Young (YA; n = 32; 18 males, aged 26.2 ± 5.3 yrs.) and Older (OA; n = 12; 3 males, aged 62.4 ± 6.7 yrs.) adults were assessed for objective (visual acuity, contrast sensitivity, depth perception, and lower peripheral vision), and subjective visual function (VFQ-25) along with motion sickness susceptibility. Subjective Visual Vertical (SVV) and induced nausea and vection were assessed using the Rod and Disc Test (RDT). Groups were compared using Mann-Whitney U, whilst determinants of SVV variability were evaluated using Multiple regression modelling. Visual acuity (p < 0.01) and contrast sensitivity (p = 0.04) were lower in OA. Visual dependence (SVV tilt errors) was not associated with ageing (p = 0.46). YA experienced greater RDT-induced vection (p = 0.03). Visual acuity and contrast sensitivity accounted for modest proportions of variance in SVV tilt errors (VA; R2 = 0.14, F(1,42) = 8.00, p < 0.01; β = 6.37) and (CS; R2 = 0.06, F(1,42) = 3.93, p = 0.05; β = −4.97), respectively. Our findings suggest that subclinical differences in visual acuity and contrast sensitivity contribute to SVV tilt error variability, among both healthy young and older adults. Further studies are needed to define the inter-relationship between age-related visual function, non-visual factors (including vestibular and somatosensory fidelity, activity levels, fear of falling and cognitive function) and visual dependence.

Style harmonization of panoramic radiography using deep learning.

This study aimed to harmonize panoramic radiograph images from different equipment in a single institution to display similar styles. A total of 15,624 panoramic images were acquired using two different equipment: 8079 images from Rayscan Alpha Plus (R-unit) and 7545 images from Pax-i plus (P-unit). Among these, 222 image pairs (444 images) from the same patients comprised the test dataset to harmonize the P-unit images with the R-unit image style using CycleGAN. Objective evaluations included Frechet Inception Distance (FID) and Learned Perceptual Image Patch Similarity (LPIPS) assessments. Additionally, expert evaluation was conducted by two oral and maxillofacial radiologists on transformed P-unit and R-unit images. The statistical analysis of LPIPS employed a Student's t-test. The FID and mean LPIPS values of the transformed P-unit images (7.362, 0.488) were lower than those of the original P-unit images (8.380, 0.519), with a significant difference in LPIPS (p < 0.05). The experts evaluated 43.3-46.7% of the transformed P-unit images as R-unit images, 20.0-28.3% as P-units, and 28.3-33.3% as undetermined images. CycleGAN has the potential to harmonize panoramic radiograph image styles. Enhancement of the model is anticipated for the application of images produced by additional units.

A multi‐path residual network for image denoising based on edge prior information

AbstractEdge‐preserving denoising is important in image analysis. However, most existing methods suffer from smoothing and loss of high frequency detail at the edges. Aiming at this issue, a multi‐path residual network using edge prior information is proposed. Specifically, the edge is first recovered by a newly designed parallel edge extraction module. Then it is used as a priori to generate affine transform parameters to guide the weight distribution between noise and edge, so that the shallow feature extraction pays more attention to preserving edges. In the deep feature extraction stage, a multi‐scale attention unit is designed to provide the spatial neighbourhood information of the feature points to filter and activate the deep features, which further enhances the ability of the network to extract fine‐grained noisy features. Finally, by taking the difference between the noisy image and the noise feature obtained with residual learning, the denoised image is produced. Extensive experiments show that the PSNR is improved by 0.00–0.78 dB on grey image denoising and 0.00–2.69 dB on colour image denoising compared with others. The denoised image has a better ability to preserve image edges, high frequency details and visual perception.