Visual Images Research Articles

A novel DRL-guided sparse voxel decoding model for reconstructing perceived images from brain activity

BackgroundDue to the sparse encoding character of the human visual cortex and the scarcity of paired training samples for {images, fMRIs}, voxel selection is an effective means of reconstructing perceived images from fMRI. However, the existing data-driven voxel selection methods have not achieved satisfactory results. New methodHere, a novel deep reinforcement learning-guided sparse voxel (DRL-SV) decoding model is proposed to reconstruct perceived images from fMRI. We innovatively describe voxel selection as a Markov decision process (MDP), training agents to select voxels that are highly involved in specific visual encoding. ResultsExperimental results on two public datasets verify the effectiveness of the proposed DRL-SV, which can accurately select voxels highly involved in neural encoding, thereby improving the quality of visual image reconstruction. Comparison with existing methodsWe qualitatively and quantitatively compared our results with the state-of-the-art (SOTA) methods, getting better reconstruction results. We compared the proposed DRL-SV with traditional data-driven baseline methods, obtaining sparser voxel selection results, but better reconstruction performance. ConclusionsDRL-SV can accurately select voxels involved in visual encoding on few-shot, compared to data-driven voxel selection methods. The proposed decoding model provides a new avenue to improving the image reconstruction quality of the primary visual cortex.

In the Mind's Eye: Exploring the Relationship Between Visual Mental Imagery and Stereotyping.

How do social stereotypes shape and reflect images formed in the mind's eye? Visual mental imagery has long been assumed crucial in creating, maintaining, and perpetuating stereotypes and prejudice. Surprisingly, research in social cognition has only recently begun to explore the causal role of mental images in these phenomena. In contrast, cognitive neuroscience research on visual mental imagery (VMI) has explored the pivotal role of imagery in various consequential cognitive and behavioral phenomena. However, cognitive neuroscience has largely neglected how stereotypes influence mental imagery. This article provides a historical overview of the development of these two fields in terms of mental imagery and discusses recent advances at their intersection. Opportunities for additional integration are highlighted, and suggestions for furthering the dual study of stereotyping and mental imagery are provided. How can social stereotypes impact and mirror visual imagination? It has long been assumed that visual mental imagery plays a central role in forming, maintaining, and strengthening stereotypes and prejudice. Yet, until recently, there has been limited exploration within social psychology and cognitive neuroscience on the explicit connection between visual mental images and social stereotypes. We describe the historical progression of these fields concerning visual imagery and explore recent advancements that unite stereotyping and mental imagery research. Furthermore, we propose avenues for future research to deepen our understanding of how individuals utilize mental images in stereotyping and how mental imagery can modify stereotypes.

For Memoria Aeterna: Approaches to Immortality in Memory in Ancient Roman Funerary Monuments

When facing death, Ancient Romans attempted to achieve immortality through eternal memory. While the elites sought great achievements as invisible monuments, the non-elite Roman population depended on their tombs to preserve their identity and memory. By analyzing funerary monuments of the non-elite from the Late Republic to the first two centuries of the Roman Empire, this essay explores how their textual and visual components construct images that define and idealize the memory of individuals. The essay also investigates how these elements interact with the living to preserve and strengthen the memories of the dead: by connecting with family and friends from the private sphere in their regular visits as well as luring and informing strangers passing by from the public world. Finally, the essay sheds light on how the most important Roman festival for the dead, Parentalia, provided opportunities to appeal to both types of audiences in the preservation of memory.

Supporting recovery, healing and wellbeing with Aboriginal communities of the southeast coast of Australia: a practice-based study of an Aboriginal community-controlled health organisation’s response to cumulative disasters

BackgroundThe recent crises of bushfires, floods, and the COVID-19 pandemic on the southeast coast of Australia were unprecedented in their extent and intensity. Few studies have investigated responses to cumulative disasters in First Nations communities, despite acknowledgement that these crises disproportionately impact First Nations people. This study was conducted by Aboriginal and non-Aboriginal researchers in partnership with Waminda, South Coast Women’s Health and Wellbeing Aboriginal Corporation, an Aboriginal Community Controlled Health Organisation (ACCHO). It investigated the collective experiences of people affected by cumulative disasters to identify the practices that support healing, and recovery for Aboriginal communities. The study addresses a knowledge gap of how Waminda, designs, manages and delivers responses to address complex health and social issues in the context of cumulative disasters.MethodsUnderpinned by practice theory this study employed Indigenous-informed, narrative inquiry. Culturally-appropriate, multiple interpretive methods were used to collect data including: observations; yarns with Aboriginal community members, yarns with Waminda practitioners, management and board members; interviews-to-the-double, visual images and documentation. The data were collated and analysed using the phases of reflexive thematic analysis.ResultsThe paper articulates a suite of culturally safe and place-based practices that enhance social, emotional and spiritual well-being following cumulative disasters. These practice bundles include: adopting a Country-centred conception of local communities; being community-led; viewing care as a collective, relational, sociomaterial accomplishment and having fluid boundaries. These practice bundles ‘hang together’ through organising practices including the Waminda Model of Care, staff wellbeing framework and emergency management plan which orient action and manage risks. The paper demonstrates the need for disaster responses to be community-led and culturally situated. ACCHOs are shown to play a crucial role, and their local responses to immediate community needs are grounded in contextual knowledge and use existing resources rather than relying on mainstream system-wide interventions.ConclusionsThe paper suggests crafting responses that focus on assisting communities (re)gain their sense of belonging, hope for the future, control over their lives and their capacities to care for and to be cared for by Country, are key to both enhancing healing, health and well-being and harnessing the strengths of communities.

Digital remote monitoring of chronic retinal conditions-A clinical future tool? : Remote monitoring of chronic retinal conditions

In view of the predicted increase in incidence and prevalence of chronic retinal diseases and undersupply of care in the population, telemedicine could contribute to reducing access barriers to healthcare and improving the results of treatment. A literature review on remote monitoring of chronic retinal diseases was carried out. The medical literature was searched for publications on remote monitoring of chronic retinal diseases. The results were compiled in anarrative overview. The four main topics in the literature are: validation studies, implementation strategies, acceptance/target group analyses and health economic analyses. Remote monitoring systems are based on visual function tests, imaging or patient reports and have been particularly investigated in age-related macular degeneration (AMD) and diabetic eye disease (DED). Studies indicate positive effects regarding an optimization of clinical care and afavorable safety profile but randomized controlled trials are lacking for the majority of monitoring tools. Remote monitoring could complement existing care structures for patients with chronic retinal diseases, especially AMD and DED. Promising systems are based on hyperacuity or optical coherence tomography, while patient-reported data are not commonly used; however, there is currently insufficient evidence justifying the use of remote monitoring systems in chronic retinal diseases in Europe and more research on the validation of remote monitoring systems is needed.

Method for enhanced gesture recognition under low light conditions based on wearable mechanoluminescence sensors

Gestures, as one of the key modes of human–computer interaction, are currently identified and processed mainly through two methods: machine vision imaging and wearable stress/strain sensing.However, the former has high requirements for lighting and background.This paper innovatively proposes a feature fusion algorithm that combines mechanoluminescent sensors for gesture recognition under low-light conditions. Unlike existing methods, this algorithm creates a system that integrates mechanoluminescent sensors for visual gesture recognition. By triggering the sensor’s luminescence through mechanical stress, it provides additional light source information to enhance image quality in low-light environments.For this purpose, this study employed the fluorescent emission properties of ZnS:Cu to fabricate a mechanoluminescence sensor. Its mechanoluminescence response characteristics were measured. Based on these findings, an algorithm for the fusion of gesture information features was developed for low illumination backgrounds. This algorithm decomposes the gesture visual images through YCbCr, extracting the HOG features of the Cr channel (Cr-HOG). Simultaneously, feature fusion is performed using the pooling layer (VGG16-Conv5-pool) following the convolutional layer (Conv5-3) in the VGG16 model. A one-to-one composite SVM classifier is constructed to complete the training and testing of the gesture recognition model. Ultimately, the feasibility of this enhanced gesture recognition method was validated through unmanned vehicle control experiment. Experimental results demonstrated that in environments with an illuminance level below 10 LUX measured by a light meter, the average recognition rate of the wearable mechanoluminescence sensor feature fusion algorithm reached 95.82 %. This is 32.24 % higher than the recognition rate of the single Cr-HOG feature classification and 28.27 % higher than the single VGG16-Conv5-pool feature classification. Compared with feature extraction using ResNet-50 and DenseNet-121 networks, the recognition rate for classifying gestures under low-light conditions is approximately 30 % higher.Compared with other image enhancement recognition methods, the recognition can be increased by up to 30.88 %.

COMICS AS A MEANS OF PRESERVING CLASSICAL LITERATURE IN MODERN PEOPLE’S READING (The case of W. Shakespeare)

The article focuses on adaptations of the tragedy “Hamlet” and the comedy “A Midsummer Night’s Dream” by W. Shakespeare in the form of comic books. The object of study is the peculiarities of comics as a text in demand by the representatives of clip consciousness, which is formed under the influence of the IT. The subject of study is the peculiarities of the source text transformation in comic adaptations of the 20th–21st centuries. The study is based on two adaptations of “Hamlet” and three adaptations of “A Midsummer Night’s Dream” by W. Shakespeare. The tasks of the study were as follows: to determine the connection between the comic book genre and clip consciousness; to highlight the characteristic features of the comics genre; to analyse the reflection of genre features in concrete texts; to describe changes in the source text depending on the nature of the audience. The study showed that the popularity of comics as a genre is inextricably linked with the emergence of clip consciousness. Certain features of the comics genre correlate with those of clip consciousness: fragmentation corresponds to mastering information in small portions, the emphasis on the visual presentation of information is associated with the perception of the world through visual images.

An improved YOLOv8-CGA-ASF-DBB method for multi-class wear debris recognition of online visual ferrograph image

Abstract The analysis of wear based on On-Line Visual Ferrograph (OLVF) provides crucial insights for the analysis of wear faults in mechanical equipment.However, online ferrograph analysis has been greatly limited by the low imaging quality and recognition accuracy of particle chains and high hubbles when analyzing lubricant oils in practical applications. To address this issue,this paper proposes an enhanced OLVF wear image detection model based on YOLOv8 and applies it to the multi-class intelligent recognition of ferrograph images .The Cascade Group Attention(CGA) module is introduced enhance the diversity of features and improve computational efficiency. The fusion of attention scale sequence is introduced to achieve precise and rapid recognition of small targets. This Diverse Branch Block(DBB) module is introduced efficiently extracts features without compromising reasoning speed during training. For verification , a test of the bridge transmission box was conducted based on OLVF, and 992 ferrograph images were collected. Experimental results reveal that the improved algorithm achieves an accuracy of 94.53% on the dataset of bridge transmission box ferrograph wear debris images collected through OLVF. This represents a 5.2% increase in recognition accuracy compared to the original algorithm, while maintaining a processing time of only 0.69ms per image. These findings provide compelling evidence for the significant enhancements in both recognition accuracy and processing speed achieved by the improved algorithm, thereby establishing its considerable value for engineering applications.

Kinematic Properties of Haptic-Free Reach-to-Grasp Movements in Virtual Reality: A Comparison with Natural Prehension in Real Spaces and Pantomimed Ones

Many researchers are interested in how the kinematics of reach-to-grasp movements in virtual reality (VR), which involve the vergence–accommodation conflict, differ from real space. The present study, conducted in VR, verified the effect of a discrepancy between visual and haptic target size and found that terminal haptic feedback is weighted more heavily than visual information, as is the case in real space. Furthermore, we investigated how the presence or absence of terminal haptic feedback modulates performance in VR by comparing prehension with or without terminal haptic feedback in VR, closed-loop natural grasping in real space, and pantomimed prehension with the eyes closed. Our results suggested that the contribution of a visual image to grip aperture adjustment is quite marginal in situations where terminal haptic feedback is unavailable, and that the performance in VR without haptic feedback is highly correlated with performances driven by fully internal representations (i.e., pantomimed movements).

Classification of wheat flour levels in powdered spices using visual imaging

The present research aims to investigate the ability of image processing in the detection of wheat flour adulterant in different spices. Different samples of black pepper, red pepper, and cinnamon were prepared with different levels of wheat flour adulteration. The images of the samples were captured using a visible camera. An image processing algorithm was designed and codded in MATLAB software to process the acquired images. Different color and textural features were extracted. The efficient features were selected and classified using artificial neural network and support vector machine. In the present research, the classification accuracies of artificial neural network analysis for black pepper, red pepper, and cinnamon products were 97.8, 100.00, and 100.00 %, respectively. During the experiment, these results were better than the performance of the support vector machine, (93.33, 100.00, and 98.88 %, respectively). Visible image processing can be used accurately to detect different adulterant levels that increase product quality while reducing operating costs.

Recognition of Molecular Structure of Phosphonium Salts from the Visual Appearance of Material with Deep Learning Can Reveal Subtle Homologs.

Determining molecular structures is foundational in chemistry and biology. The notion of discerning molecular structures simply from the visual appearance of a material remained almost unthinkable until the advent of machine learning. This paper introduces a pioneering approach bridging the visual appearance of materials (both at the micro- and nanostructural levels) with traditional chemical structure analysis methods. Quaternary phosphonium salts are opted as the model compounds, given their significant roles in diverse chemical and medicinal fields and their ability to form homologs with only minute intermolecular variances. This research results in the successful creation of a neural network model capable of recognizing molecular structures from visual electron microscopy images of the material. The performance of the model is evaluated and related to the chemical nature of the studied chemicals. Additionally, unsupervised domain transfer is tested as a method to use the resulting model on optical microscopy images, as well as test models trained on optical images directly. The robustness of the method is further tested using a complex system of phosphonium salt mixtures. To the best of the authors' knowledge, this study offers the first evidence of the feasibility of discerning nearly indistinguishable molecular structures.

Efficient Broadband Near‐Infrared Emitters in Lead‐Free Metal Halides with Record Photoluminescence Quantum Yield Under Blue Light Excitation

AbstractRealizing ultra‐efficient broadband near‐infrared (NIR) luminescence, especially under blue light excitation, remains an enormous challenge in lead‐free metal halides. Herein, the efficient NIR emission under blue light excitation is achieved in Sb3+‐doped 0D (ETPP)2ZnCl4xBr4‐4x (x = 0–1) (ETPP+ = (Ethyl)triphenylphosphonium) through coordination structure modulation and halogen substitution. Compared with the visible light emission of Sb(III)‐based compounds, the emission in Sb3+‐doped (ETPP)2ZnCl4xBr4‐4x shifts to the NIR region due to the large excited state lattice distortion. Parallelly, the excitation bands gradually shift from 376 to 450 nm as Br gradually replaces Cl, and the emission bands can further shift from 702 to 763 nm. Thus, the broadband NIR emission at 763 nm with a record luminous efficiency of 55.4% under 450 nm excitation can be achieved in Sb3+‐doped compounds. Moreover, the large‐scale synthesis technique of Sb3+‐doped (ETPP)2ZnBr4: NIR phosphors at room temperature is further developed and this compound exhibits impressive thermal and chemical‐stabilities. Finally, a high‐performance NIR light‐emitting‐diode is fabricated by combining a commercial blue chip and (ETPP)2ZnBr4:10%Sb3+ phosphors, which shows the most advanced photoelectric efficiency (17.8%) and output power (67.7 mW) in lead‐free metal halides. Thus, the as‐fabricated device is further demonstrated in the applications of night vision and biomedical imaging.

About Research - Qualitative Data Collection: Photo Elicitation.

Photo elicitation is a qualitative data collection technique in which the researcher includes photographs or other visual images as part of participant interviews. The researcher might provide the photographs or might ask the participants to bring photographs to the interview. This technique enhances the breadth and depth of verbal qualitative interviews. The use of photo elicitation can enhance the rigor of a qualitative study. There are both advantages and disadvantages of this data collection technique. Ethical issues warrant special consideration.

Efficient and Near-Zero Thermal Quenching Cr3+-Doped Garnet-Type Phosphor for High-Performance Near-Infrared Light-Emitting Diode Applications.

In recent years, near-infrared (NIR) phosphors have attracted great research interest due to their unique physical properties and broad application prospects. However, obtaining NIR phosphors with both high quantum efficiency and excellent thermal stability remains a great challenge. In this study, novel NIR Ca3Mg2ZrGe3O12:Cr3+ phosphors were successfully prepared using a high-temperature solid-phase method, and the structure and luminescent properties of the material were systematically investigated. Ca3Mg2ZrGe3O12:0.01Cr3+ emits NIR light in the range of 600 to 900 nm with a peak at 758 nm and a half-height width of 89 nm under the excitation of 457 nm blue light. NIR luminescence shows considerable quantum efficiency, and the internal quantum efficiency of the optimized sample is up to 68.7%. Remarkably, the Ca3Mg2ZrGe3O12:0.01Cr3+ phosphor exhibits a near-zero thermal quenching behavior, and the luminescence intensity of the sample at 250 °C maintains 92% of its intensity at room temperature. The mechanism of high thermal stability has been elucidated by calculating the Huang Kun factor and activation energy. Finally, NIR pc-LED devices prepared from Ca3Mg2ZrGe3O12:0.01Cr3+ phosphor with commercial blue LED chips have good performance, proving that this Ca3Mg2ZrGe3O12:0.01Cr3+ NIR phosphor has potential applications in night vision and biomedical imaging.

Retrospective denoising and sharpening effects on postmortem computed tomography images of formalin-fixed human cadavers for human anatomy education and research

BackgroundThe value of formalin-fixed postmortem computed tomography (PMCT) has significantly increased in human anatomy education and research. However, improving embalmed PMCT images with high noise, low contrast, and multiple artifacts is an important challenge in enhancing the quality of clinical images. Retrospective denoising methods for embalmed PMCT data are essential for anatomical education and research when new-generation CT scanners with denoising functions are unavailable. MethodsThe three currently available standalone software denoising methods, including image summation methods (Fused CT), noise-reduction system methods (iNoir), and iterative reconstruction (IR, SafeCT), were used to analyze the retrospective noise-reduction effect on 13 human formalin-fixed PMCT datasets. ResultsFused CT had some advantages; however, it was not useful for embalmed cadavers because of high noise, which doubled with the addition. iNoir and SafeCT improved the visual image quality of the noisy cadaver images. Statistical examination showed a 22–67 % and 18–56 % improvement in noise reduction in the non-artifact and metal artifact parts, respectively, depending on the methods and denoising intensities. However, this improvement was not statistically or morphologically significant in the presence of strong metal artifacts. In contrast, the scattered metal and streak artifacts peculiar to cadaveric images showed effective morphological and statistical improvement. ConclusionsRetrospective denoising of embalmed PMCT images showed significant morphological and statistical improvements in noise reduction and is feasible for current anatomy education and research.

Innovations in seafood freshness quality: Non-destructive detection of freshness in Litopenaeus vannamei using the YOLO-shrimp model

The relationship between freshness changes and visual images of Litopenaeus vannamei was established based on Sensory Evaluation, Total Volatile Base Nitrogen (TVB-N), Total Viable Count (TVC), and Gray Value during storage at 4 °C. A non-destructive detection system using the advanced YOLO(You Only Look Once)-Shrimp model was developed to evaluate shrimp freshness. The results revealed a gradual increase in freshness indices over time, with the gray value showing strong positive correlations with TVB-N and TVC (0.88 and 0.81). The advanced YOLO-Shrimp model demonstrated notable performance enhancements over the YOLOv8 model, as evidenced by a precision increase of 5.07 %, a recall improvement of 1.58 %, a 3.25 % rise in the F1 score, and a 2.84 % elevation in mAP50. This innovative approach offers substantial potential for enhancing food safety and quality control in the seafood industry.

Development of analytical methods and method validation for the qualitative and quantitative determination of Carboxymethyl Cellulose (CMC) in yogurt and ayran

This study presents the development and validation of analytical methods for the qualitative and quantitative determination of Carboxymethyl Cellulose (CMC) in yogurt and ayran. The methods were evaluated for their detection limit (LOD), quantification limit (LOQ), and method detection limit (MDL) across multiple samples, demonstrating robust sensitivity with MDL and LOD values of 0.03% for both yogurt and ayran. Recovery studies showed high accuracy, with recovery rates between 98% and 100%, and consistent recovery within the acceptable range of 97–103%, reinforcing the methods' reliability. The quantitative analysis exhibited strong repeatability and reproducibility, with low relative standard deviations (RSDr and RSDR), confirming minimal intra-day and inter-day variability. The calibration curves for CMC analysis demonstrated excellent linearity with high coefficients of determination (R2 = 0.9985 for yogurt and 0.9951 for ayran), ensuring accurate quantification over a wide concentration range. Measurement uncertainty analysis further validated the methods' precision and accuracy, showing low relative uncertainties for trueness, repeatability, and reproducibility. Robustness evaluations indicated that the methods maintained consistent recovery rates despite variations in pH, heating time, and sample quantity, highlighting their reliability under different conditions. For qualitative analysis, the visual images method showed exceptional performance with perfect sensitivity and specificity, accurately identifying all positive and negative samples without any false positives or negatives. This high level of accuracy makes the visual images method a valuable tool for ensuring product safety and compliance with quality standards in the dairy industry. Overall, the validated analytical methods for CMC detection in yogurt and ayran demonstrated high precision, accuracy, and reliability, making them essential for quality control and regulatory compliance in dairy production.

Sentinel mechanism for visual semantic graph-based image captioning

Image captioning aims to generate a description of a given image. However, inherent representation differences between images and sentences make it difficult to align semantic meanings for captioning. Inspired by the human cognitive processes of understanding and describing images, a visual semantic sentinel mechanism based image captioning framework is proposed in this paper. Specifically, we introduce attribute nodes to enable a more comprehensive description of the objects and model the high-level relationships within a visual semantic graph. Then, the visual semantic sentinel mechanism is proposed to simulate the process of sentence generation. visual semantic graphs, visual features and previous language information in generated words are integrated with a semantic sentinel mechanism to align vision-language information and get contextually relevant descriptions of images. Comprehensive experiments on the challenging MS-COCO demonstrate our method outperforms the previous state-of-the-art methods. The code is publicly available at https://github.com/superatops/SSVSG.

Deep learning with ensemble approach for early pile fire detection using aerial images

Wildfires rank among the world’s most devastating and expensive natural disasters, destroying vast forest resources and endangering lives. Traditional firefighting methods, reliant on ground crew inspections, have notable limitations and pose significant risks to firefighters. Consequently, drone-based aerial imaging technologies have emerged as a highly sought-after solution for combating wildfires. Recently, there has been growing research interest in autonomous wildfire detection using drone-captured images and deep-learning algorithms. This paper introduces a novel deep-learning-based method, distinct in its integration of infrared thermal, white, and night vision imaging to enhance early pile fire detection, thereby addressing the limitations of existing methods. The study evaluates the performance of machine learning algorithms such as random forest (RF) and support vector machines (SVM), alongside pre-trained deep learning models including AlexNet, Inception ResNetV2, InceptionV3, VGG16, and ResNet50V2 on thermal-hot, green-hot, and white-green-hot color images. The proposed approach, particularly the ensemble of ResNet50V2 and InceptionV3 models, achieved over 97% accuracy and over 99% precision in early pile fire detection on the FLAME dataset. Among the tested models, ResNet50V2 excelled with the thermal-fusion palette, InceptionV3 with the white-hot and green-hot fusion palettes, and VGG16 with a voting classifier on the normal spectrum palette dataset. Future work aims to enhance the detection and localization of pile fires to aid firefighters in rescue operations.

Multi-Modal Machine Learning to Predict the Energy Discharge Levels from a Multi-Cell Mechanical Draft Cooling Tower

An artificial neural network was developed to augment the accuracy of a physically based computer model in relating heat discharge to visible plume volume of a 12-cell mechanical draft cooling tower. In a previous study, Savannah River National Laboratory developed a 1D model to capture the average power plant discharge levels via analysis of a series of visual images but was unable to accurately predict individual cases, resulting in an overall average error of about 5%, but individual comparisons resulted in an R2 of 0.36. Three optimization algorithms were applied to better fit the entrainment coefficients, and the artificial neural network model was applied to 289 cases of a 12-cell mechanical draft cooling tower power generation facility. Two artificial neural networks configurations consisted of 10 and 47 nodes that used as input readily available plant data, observed cooling tower plume conditions, observed operational conditions, local and regional weather, and the predicted plume volume from the physical model; the individual predictions’ accuracy improved to R2>0.95. This article concludes the sensitivities for the 1D model and additional actions to progress this field of study as well as applications for cooling tower monitoring. This strategy demonstrated an encouraging first step towards using multi-modal artificial neural network machine learning technology for information fusion to estimate power levels from external observations.