Visual Images Research Articles

Evaluation of Landscapes and Soundscapes in Traditional Villages in the Hakka Region of Guangdong Province Based on Audio-Visual Interactions

Traditional villages in the Hakka region of Guangdong Province have attracted significant attention for their unique cultural heritage and traditional lifestyles. Their favourable audio-visual environments offer immersive and realistic experiences for both residents and visitors. Thus, we selected four representative villages and used semantic segmentation to extract the core visual elements (sky, vegetation, construction, and dynamic) from visual landscape images. Audio-visual interaction experiments and subjective surveys were conducted to investigate the participants’ evaluations of the visual landscape and soundscape to explore the mechanisms of audio-visual interaction. The results revealed that different audio-visual combinations significantly influenced the participants’ visual landscape satisfaction, acoustic comfort, and audio-visual harmony evaluations. Specifically, visual images of natural spaces with a high proportion of sky (24.54%) and vegetation (72.56%), matched with natural sounds (with a sound pressure level of approximately 55 dB) such as birdsong, wind, and flowing water, received excellent ratings for both visual landscape satisfaction and acoustic comfort evaluations. Moreover, the findings further revealed that coordination between visual and audio materials was crucial for enhancing the participants’ perceptions and assessments, highlighting the importance of audio-visual coordination in creating harmonious environments. These findings provide recommendations for spatial planning, landscape design, and soundscape optimisation in traditional villages.

Topological importance of CD8+ T-cell enrichment in the tumor microenvironment of classic Hodgkin lymphoma.

Classic Hodgkin lymphoma (CHL) histologically consists of Hodgkin Reed-Sternberg (HRS) cells and the tumor microenvironment (TME), but the relationship between TME characteristics and clinical features of CHL remains unclear. We aimed to investigate the effects of the TME structure on the outcomes of patients with CHL. We performed a high-throughput analysis of HRS cells and their topological relationship with the reactive immune cells in the TME. After multiplexed immunofluorescence labeling against CD4, CD8, CD30, CD68, CD163, PD-1, and PD-L1, visual images were analyzed. Phenotypes were assigned to all reactive cells, such as CD4+ and CD8+ T-cells and macrophages. Since the densities of PD1+/CD4+ T-cells, CD8+ T-cells, and PD-L1+ macrophages were significantly higher in the area < 60μm than in the area < 120μm from each HRS cell in 45 tissue samples from 34 patients with CHL, we further analyzed the TME-component cells by focusing on the 60μm radius in the initial samples. TMEs containing > 15 CD8+ T-cells were associated with a significantly better 3-year progression-free survival than those with ≤ 15 CD8+ T-cells (100% vs. 53%, p = 0.006). In comparison with TMEs containing ≤ 15 CD8+ T-cells, TMEs containing > 15 CD8+ T-cells had significantly more PD-L1- macrophages (mean 3 vs. 1 cell, p = 0.015) and fewer PD-1+/CD4+ T-cells (mean 16 vs. 28 cells, p = 0.036). Epstein-Barr virus positivity in HRS cells was significantly associated with a higher number of macrophages in the 60μm radius area. In conclusion, the TME structure in patients with CHL can differ, enabling precision therapies.

A Multimodal Social Semiotic Analysis of Typography and Layout in ‘’Alexander Master’s Novel Stuart: A Life Backwards’’

The output of multimodal texts has increased over the past 20 years due to advances in technology and culture, which has accelerated the demand for tackling multimodal additional semiotic modes for meaning making, such as typography, layout ,visual images, colour, etc. The theory of multimodality, as supposed by Kress and Van Leeuwen (2001–2006), Baldry and Thibaut (2006), is applied to a potential framework for the analysis of multimodal novels that use not only wording structure but also many semiotic modes in the formation of meaning. The social approach to multimodality, in brief, is based on Halliday's linguistic description and adhered to the multimodal assumption that "mutual propositions are employed and worked together in various modes" (Kress and Leeuwen,2002:3). Thus, Kress and Van Leeuwen (1996:39), in their book ‘’Reading Images’’ investigate the level for which the underlying theories of Halliday's framework to language are feasible and applicative to visual communicative management, and they create a visual system that mostly makes use of Halliday's principles and concepts. The study is concerned with the investigation of a multimodal analysis of the multiple elements of various modes of typographic devices, and layout design used in the selected novel. This selected text ‘’Stuart: A Life Backwards’’ is a multimodal novel since the writer Masters does not rely on linguistic verbal tools, he extends them to incorporate a variety of visual semiotic modes and graphic communicative elements that will intensify his understanding of storytelling and narrative development. The study has shown that an extension to the mode of wording formation is performed in the multimodal analysis by incorporating more multimodal tackling features of typographic principles and layout framing devices in creating an appropriate comprehensive meaning construction in Masters’ selected narration.

Autonomous Landing Guidance for Quad-UAVs Based on Visual Image and Altitude Estimation

In this paper, an autonomous landing guidance strategy is proposed for quad-UAVs, including landing marker detection, altitude estimation, and adaptive landing commands generation. A double-layered nested marker is designed to ensure that the marker can be captured both in high and low altitudes. A deep learning-based marker detection method is designed where the intersection of union is replaced by the normalized Wasserstein distance in the computation of non-maximum suppression to improve the detection accuracy. The UAV altitude measured by inertial measurement unit is fused with vision-based altitude estimation data to improve the accuracy during the landing process. An image-based visual servoing method is designed to guide the UAV approach to the landing marker. Both simulation and flight experiments are conducted to verify the proposed strategy.

Relationship Between Intraocular Pressure and the True Rate of Functional and Structural Progression in the United Kingdom Glaucoma Treatment Study.

To investigate the effect of average intraocular pressure (IOP) on the true rate of glaucoma progression (RoP) in the United Kingdom Glaucoma Treatment Study (UKGTS). UKGTS participants were randomized to placebo or Latanoprost drops and monitored for up to two years with visual field tests (VF, 24-2 SITA standard), IOP measurements, and optic nerve imaging. We included eyes with at least three structural or functional assessments (VF with <15% false-positive errors). Structural tests measured rim area (RA) with Heidelberg retina tomography (HRT) and average peripapillary retinal nerve fiber layer (pRNFL) thickness with optical coherence tomography (OCT). One eye of 436 patients (222 on Latanoprost) was analyzed. A Bayesian hierarchical model estimated the true RoP of VF and structural metrics, and their correlations, using sign-reversed multivariable exponential distribution. RA and pRNFL measurements were converted to a dB scale, matching the VF metric (mean deviation [MD]). The effect of average IOP on the true RoPs was estimated. True RoP at the mean average IOP (17 mm Hg) was faster (P < 0.001) for VF-MD (-0.59 [-0.73, -0.48] dB/year) than HRT-RA (-0.05 [-0.07, -0.03] dB/year) and OCT-pRNFL (-0.08 [-0.11, -0.06] dB/year). The proportional acceleration of RoP per mm Hg increase was, however, not significantly different (smallest P = 0.15). Accounting for the structural floor-effect largely eliminated the differences in RoPs (smallest P = 0.25). VF appeared to deteriorate at a faster rate than structural measurements. However, this could be explained by the floor-effect from nonfunctional tissue. IOP induced a similar acceleration in RoP per mm Hg increase.

Total variational noise reduction method for EBAPS image based on weighted nuclear norm minimization

The electron-bombarded active pixel sensor (EBAPS) is a highly sensitive vacuum-solid hybrid low-light imaging device capable of functioning in ultra-low illumination environments as low as 10-4 lx. However, this high sensitivity also causes problems, such as a low signal-to-noise ratio and complex noise. To enhance the quality of low-light night vision images captured by EBAPS and achieve effective imaging in ultra-low illumination, this study proposes a noise reduction algorithm based on the noise characteristics of EBAPS images. By utilizing the weighted nuclear norm minimization (WNNM) as the fundamental framework, several enhanced methods to address the multi-source noise of the EBAPS under ultra-low illumination have been proposed. These methods include outlier removal and variance-stabilizing transformation. To address the lack of edge preservation, a four-directional total variational regularization term has been incorporated into the WNNM model to maintain the image edge. Experimental results demonstrated that the improved method effectively eliminates various types of EBAPS noise while considerably returning the edges, ultimately enhancing the quality of low-light images. This study greatly facilitates subsequent applications of the low-light night vision technology.

Visual Performance and Predictive OCT Biomarkers in Epiretinal Membrane Assessment: Beyond Distance Visual Acuity.

This study aimed to comprehensively assess visual performance in eyes with idiopathic epiretinal membrane (iERM). Additionally, it sought to explore the associations between optical coherence tomography (OCT) imaging biomarkers and visual performance in patients with iERM. In this prospective, non-interventional study, 57 participants with treatment-naïve iERM from the University of Turin, between September 2023 and March 2024 were enrolled. Visual performance was measured using distance best-corrected visual acuity (BCVA), near BCVA, and maximum reading speed (MaxRS). Structural retinal imaging biomarkers were obtained from OCT, focusing on retinal layer thicknesses and epiretinal membrane characteristics. Statistical analyses, including linear regression and multivariate analysis, were used to determine relationships between visual function and imaging metrics. Monocular distance BCVA (0.37 ± 0.23 LogMAR), near BCVA (0.59 ± 0.18 LogMAR), and MaxRS (108.88 [68.38] words perminute [wpm]) in patients with iERM were significantly reduced compared with reference values. Both near BCVA and reading speed exhibited a greater percentage reduction than distance visual acuity. Patients with phakic showed worse visual acuity than patients with pseudophakia, although their reading performance was similar. Higher outer plexiform layers thickness and inner retinal thickness were associated with decreased distance and near visual acuity and reduced reading speed (beta, P value). The iERM predominantly impacts near visual performance, with near visual acuity and reading speed being more affected than distance visual acuity. Structural OCT biomarkers, particularly retinal thickness in specific regions, correlate with worse functional impairments. This highlights the importance of near vision assessments and imaging biomarkers for a comprehensive evaluation of visual impairment in iERM.

Staging of prostate Cancer with ultra-fast PSMA-PET scans enhanced by AI.

PSMA-PET is a reference standard examination for patients with prostate cancer, but even using recently introduced digital PET detectors image acquisition with standard field-of-view scanners is still in the range of 20min. This may cause limited access to examination slots because of the growing demand for PSMA-PET. Ultra-fast PSMA-PET may enhance throughput but comes at the cost of poor image quality. The aim of this manuscript is to evaluate the accuracy of AI-enhanced ultra-fast PSMA-PET for staging of patients with prostate cancer. A total number of 357 whole-body [68Ga]Ga-PSMA-11 PET datasets were included. Patients underwent two digital PET scans, one at standard and one at ultra-fast speed (table speed: 0.6-1.2mm/s vs. 50mm/s). A modified pix2pixHD generative adversarial network to enhance the ultra-fast images was trained with 286 datasets and evaluated with the remaining 71 datasets. The staging accuracy of ultra-fast PSMA-PET and AI-enhanced ultra-fast PET was compared with the reference standard PET separately for miTNM regions proposed by PROMISE V2.0. The AI-network significantly improved the visual image quality and detection rate in most miTNM regions compared with the non-enhanced image data (T: 69.6% vs. 43.5%, p < 0.05; N: 46.3% vs. 27.8%, p < 0.01; M1a 64.4% vs. 47.5%, p < 0.01; M1b: 85.7% vs. 72.1%, p < 0.01). However, improvement was not significant for the M1c category (42.9 vs. 28.6%, p > 0.05). Missed lesions had a smaller SUVmax and lesion size compared with detected lesions (exemplary for N: 9.5 vs. 26.5 SUVmax; 4 vs. 10mm). SUVmax values of lesions were significantly different in all miTNM regions between the ultra-fast and reference standard PET, but only in the T-region between the AI-enhanced and reference standard PET. The AI-based image enhancement improved image quality and region detection rates by a mean of 17.9%. As the sensitivity of synthetic PET for small and low-uptake lesions was limited, a potential clinical use case could be disease monitoring in patients with high tumor volume and PSMA uptake undergoing PSMA radioligand therapy. The improvement in detection rate of distant metastases was not significant. This indicates that more training data is needed to ensure robust results also for lesions that have lower appearance frequency. Future studies on accelerated PSMA-PET seem warranted.

A vision-language foundation model for precision oncology.

Clinical decision-making is driven by multimodal data, including clinical notes and pathological characteristics. Artificial intelligence approaches that can effectively integrate multimodal data hold significant promise in advancing clinical care1,2. However, the scarcity of well-annotated multimodal datasets in clinical settings has hindered the development of useful models. In this study, we developed the Multimodal transformer with Unified maSKed modeling (MUSK), a vision-language foundation model designed to leverage large-scale, unlabelled, unpaired image and text data. MUSK was pretrained on 50 million pathology images from 11,577 patients and one billion pathology-related text tokens using unified masked modelling. It was further pretrained on one million pathology image-text pairs to efficiently align the vision and language features. With minimal or no further training, MUSK was tested in a wide range of applications and demonstrated superior performance across 23 patch-level and slide-level benchmarks, including image-to-text and text-to-image retrieval, visual question answering, image classification and molecular biomarker prediction. Furthermore, MUSK showed strong performance in outcome prediction, including melanoma relapse prediction, pan-cancer prognosis prediction and immunotherapy response prediction in lung and gastro-oesophageal cancers. MUSK effectively combined complementary information from pathology images and clinical reports and could potentially improve diagnosis and precision in cancer therapy.

Salience maps for judgments of frontal plane distance, centroids, numerosity, and letter identity inferred from substance-invariant processing.

A salience map is a topographic map that has inputs at each x,y location from many different feature maps and summarizes the combined salience of all those inputs as a real number, salience, which is represented in the map. Of the more than 1 million Google references to salience maps, nearly all use the map for computing the relative priority of visual image components for subsequent processing. We observe that salience processing is an instance of substance-invariant processing, analogous to household measuring cups, weight scales, and measuring tapes, all of which make single-number substance-invariant measurements. Like these devices, the brain also collects material for substance-invariant measurements but by a different mechanism: salience maps that collect visual substances for subsequent measurement. Each salience map can be used by many different measurements. The instruction to attend is implemented by increasing the salience of the to-be-attended items so they can be collected in a salience map and then further processed. Here we show that, beyond processing priority, the following measurement tasks are substance invariant and therefore use salience maps: computing distance in the frontal plane, computing centroids (center of a cluster of items), computing the numerosity of a collection of items, and identifying alphabetic letters. We painstakingly demonstrate that defining items exclusively by color or texture not only is sufficient for these tasks, but that light-dark luminance information significantly improves performance only for letter recognition. Obviously, visual features are represented in the brain but their salience alone is sufficient for these four judgments.

PdSe2/NbSe2 Heterojunction Photodetector with Broadband Detection and Polarization Sensitivity.

Polarized photodetectors based on anisotropic two-dimensional (2D) materials display great potential applications in communications and optoelectronics. However, the existence of high dark current, low anisotropic ratio, and response speed limits their development. In this paper, a broadband polarization angle-dependent photodetector based on the PdSe2/NbSe2 van der Waals (vdW) heterojunction has been constructed. Characterization results show that the PdSe2/NbSe2 heterojunction photodetector can suppress the dark current effectively (NbSe2 ∼4 orders of magnitude and PdSe2 ∼1 order of magnitude compared with individual material). Meanwhile, the device exhibits a broadband detection capability ranging from 405 to 980 nm. The device shows a superior responsivity of 27 mA/W, a considerable detectivity of 9.8 × 107 Jones, a large external quantum efficiency of 528%, and an ultrafast rise/decay time of 1.6/1.9 μs at 1 V bias under 638 nm laser wavelength. The photodetector also achieves a high polarization-sensitive anisotropic ratio of ∼2.62 under 638 nm laser irradiation. In addition, the heterojunction device shows outstanding polarization imaging capabilities, which can be used as the image sensor. This work proposed a PdSe2/NbSe2 vdW heterojunction device with low dark current, broadband polarized detection, and polarized visual imaging, which will promote the development and practicality of polarization-sensitive photodetectors.

Multimodal identity work: The power of visual images for identity construction in the gig economy

Multimodal identity work: The power of visual images for identity construction in the gig economy

Leveraging vision-language prompts for real-world image restoration and enhancement

Significant advancements have been made in image restoration methods aimed at removing adverse weather effects. However, due to natural constraints, it is challenging to collect real-world datasets for adverse weather removal tasks. Consequently, existing methods predominantly rely on synthetic datasets, which struggle to generalize to real-world data, thereby limiting their practical utility. While some real-world adverse weather removal datasets have emerged, their design, which involves capturing ground truths at a different moment, inevitably introduces interfering discrepancies between the degraded images and the ground truths. These discrepancies include variations in brightness, color, contrast, and minor misalignments. Meanwhile, real-world datasets typically involve complex rather than singular degradation types. In many samples, degradation features are not overt, which poses immense challenges to real-world adverse weather removal methodologies. To tackle these issues, we introduce the recently prominent vision-language model, CLIP, to aid in the image restoration process. An expanded and fine-tuned CLIP model acts as an ‘expert’, leveraging the image priors acquired through large-scale pre-training to guide the operation of the image restoration model. Additionally, we generate a set of pseudo-ground-truths on sequences of degraded images to further alleviate the difficulty for the model in fitting the data. To imbue the model with more prior knowledge about degradation characteristics, we also incorporate additional synthetic training data. Lastly, the progressive learning and fine-tuning strategies employed during training enhance the model’s final performance, enabling our method to surpass existing approaches in both visual quality and objective image quality assessment metrics.

Glaucoma detection and staging from visual field images using machine learning techniques.

In this study, we investigated the performance of deep learning (DL) models to differentiate between normal and glaucomatous visual fields (VFs) and classify glaucoma from early to the advanced stage to observe if the DL model can stage glaucoma as Mills criteria using only the pattern deviation (PD) plots. The DL model results were compared with a machine learning (ML) classifier trained on conventional VF parameters. A total of 265 PD plots and 265 numerical datasets of Humphrey 24-2 VF images were collected from 119 normal and 146 glaucomatous eyes to train the DL models to classify the images into four groups: normal, early glaucoma, moderate glaucoma, and advanced glaucoma. The two popular pre-trained DL models: ResNet18 and VGG16, were used to train the PD images using five-fold cross-validation (CV) and observed the performance using balanced, pre-augmented data (n = 476 images), imbalanced original data (n = 265) and feature extraction. The trained images were further investigated using the Grad-CAM visualization technique. Moreover, four ML models were trained from the global indices: mean deviation (MD), pattern standard deviation (PSD) and visual field index (VFI), using five-fold CV to compare the classification performance with the DL model's result. The DL model, ResNet18 trained from balanced, pre-augmented PD images, achieved high accuracy in classifying the groups with an overall F1-score: 96.8%, precision: 97.0%, recall: 96.9%, and specificity: 99.0%. The highest F1 score was 87.8% for ResNet18 with the original dataset and 88.7% for VGG16 with feature extraction. The DL models successfully localized the affected VF loss in PD plots. Among the ML models, the random forest (RF) classifier performed best with an F1 score of 96%. The DL model trained from PD plots was promising in differentiating normal and glaucomatous groups and performed similarly to conventional global indices. Hence, the evidence-based DL model trained from PD images demonstrated that the DL model could stage glaucoma using only PD plots like Mills criteria. This automated DL model will assist clinicians in precision glaucoma detection and progression management during extensive glaucoma screening.

RAY:-Underwater Robot for Environmental Safety and Monitoring

In recent years, the demand for advanced human detection technologies has surged, driven by applications in security, search and rescue operations, and human-robot interaction. This paper presents an innovative approach to human detection using multiple sensor modalities, including infrared (IR), ultrasonic, and visual imaging, integrated into a mobile robotic platform. The proposed system aims to enhance detection accuracy, reduce false positives and improve response times in diverse environments. The robot is equipped with an array of sensors: infrared sensors detect heat signatures, ultrasonic sensors measure distance through sound waves, and visual cameras provide real-time image processing capabilities. The fusion of these data sources is achieved through a multi-layered machine learning algorithm, allowing the robot to make informed decisions based on the contextual information it gathers. This approach not only enhances the robot's ability to detect humans in various conditions such as low light or obstructed views but also enables adaptive learning, allowing the system to improve its accuracy over time through exposure to diverse scenarios. Testing in real-world environments demonstrates the effectiveness of the multi-sensor framework. Results indicate a significant reduction in false detection rates compared to single-sensor systems, highlighting the robustness of the approach. The implementation of this multi-sensor human detection robot has the potential to transform applications in surveillance, safety monitoring, and autonomous assistance, paving the way for more intelligent and responsive robotic systems in the future.

Deep Learning-Assisted Discovery of Analogy-Inspired Designs within Peter Collins Analogical Architectural Design Classification Framework

This study focuses on analogical reasoning and deep learning models to enhance the innovative design process in architecture. By constructing multi-layered artificial neural networks, deep learning can derive analogical predictions from structured data to solve complex tasks. Deep learning models interact with analogical thinking patterns in the architectural design process, enabling designers to analyze and draw inspiration from analogical design examples. This study aims to develop a deep learning model that categorizes architectural design examples into specific analogical design classifications. For this purpose, a model based on Convolutional Neural Networks was developed and coded in the Google Colab environment using a dataset of 29,596 visual images, employing Peter Collins' classification system of biological, mechanical, gastronomic, and linguistic analogies. During the training process, the model was trained on images classified according to biological, mechanical, gastronomic, and linguistic categories, achieving an accuracy rate of 98%; however, this rate was recorded as 86% during the testing phase. It was observed that adjustments in the learning rate parameter balanced classification accuracy and training time; lower learning rates reduced accuracy while extending training time. Despite the complexity of architectural images indicated by the 86% accuracy rate on test data, the study emphasizes the model's capacity to achieve accuracy above 95% when confronted with distinct architectural features. In this case, the model allows designers to discover which analogical classification the architectural work to be tested is designed according to, allowing them to develop creative solutions to new design problems. Additionally, this research establishes an interdisciplinary dialogue between artificial intelligence and architecture, providing a foundation for future studies.

FUZZY REGION MERGING WITH HIERARCHICAL CLUSTERING TO FIND OPTIMAL INITIALIZATION OF FUZZY REGION IN IMAGE SEGMENTATION

One of the most important goals in image segmentation is the process of separating the object parts from the image background. Image segmentation is also a fundamental stage in the development of other image applications such as object recognition, target tracking, computer vision, and biomedical image processing. Interactive image segmentation methods with additional user interaction are still popular in research. Interactive image segmentation aims to provide additional information through simple interactions, especially in images with complex objects. Interactive image segmentation with region merging processes has drawbacks, one of which is suboptimal region splitting due to soft color shades, blurred contours, and uneven lighting, referred to in this study as ambiguous regions. However, in the fuzzy region initialization stage after obtaining values from the marker process, there is a possibility of missing or suboptimal determination of fuzzy regions. This is because it only takes the highest gray level value for the background marker and the lowest gray level value for the object marker. In this study, fuzzy region merging using hierarchical clustering is proposed to find optimal initialization for fuzzy regions in image segmentation. Based on the experimental results, the proposed method can achieve optimal segmentation with an average misclassification error value of 2.62% for Natural Images and 9.33% for Dental Images.

MKGFA: Multimodal Knowledge Graph Construction and Fact-Assisted Reasoning for VQA

Knowledge-based visual question answering relies on open-ended external knowledge and a fine-grained comprehension of both the visual content of images and semantic information. Existing methods for utilizing knowledge have the following limitations: (1) Language pre-training methods output answers in the form of plain text, which only understand shallow visual content; (2) The knowledge retrieved by image objects as labels is represented as first-order logic, making it difficult to infer complex questions. To address the above problems, this paper integrates visual-textual multimodal information, accumulates domain-specific and external multi-modal knowledge, introduces and supplements external objective facts, and proposes a multimodal knowledge graph construction and fact-assisted reasoning network (MKGFA). The network consists of three parts: the multimodal knowledge graph construction module (MKGC), the objective fact-assisted reasoning module (FAR), and the answer inference module. The MKGC engages in the coarse-to-fine-grained learning of triplet representations for multimodal knowledge units. The FAR establishes deep cross-modal relations between visual objects and factual words for correlating real answers. The answer inference module makes the final decision based on the results of both. Among them, the former two modules employ a pre-training and fine-tuning strategy, systematically accumulating foundational and domain-specific knowledge. Compared with the state-of-the-arts, MKGFA achieves 1.09% and 0.7% higher accuracy on the two challenging OKVQA and KRVQA datasets, respectively. The experimental results demonstrate the complementary advantages of the integration of the two modules.

Community health promotion and disaster recovery: a PhotoVoice project in Comerío, Puerto Rico

ABSTRACT Background PhotoVoice – a series of workshops involving participatory photography and narrative-building – was employed in the rural town of Comerío, Puerto Rico (PR) to describe disaster recovery in a rural setting and foster policy dialogue. Methods Using PhotoVoice workshops and ethnographic observations, the project describes how women affiliated with a local community-based organization described the priorities for disaster recovery in visual images and narratives. We draw analytically upon theories of intersectionality and coloniality to describe socio-structural and community factors that shape community health in the context of ongoing disasters. Results Analysis indicated that gender and generational differences are key intersecting factors that mediate adaptation to disasters in this setting. Conclusions The project, which has already shown impacts on local policy decisions, demonstrates the possibilities of using PhotoVoice to foster community-driven crisis responses and policy dialogue that can shape health promotion and disaster recovery responses in PR and elsewhere.

MENGENALKAN BERAGAM PROFESI ORANG TUA PADA ANAK KELAS 1 MELALUI GAMBAR VISUAL DAN BERCERITA

The introduction and socialization of parents' professions at SD Negeri 3 Belega is part of the introduction to the school environment. The introduction of parents' professions aims to foster their understanding of the diversity of roles in society and appreciate the contribution of each profession. The introduction of this profession is full of meaning that can direct children regarding their interests and future goals. The introduction of this profession is carried out using interesting visual presentation media and storytelling. The results of this activity illustrate that the students of SD Negeri 3 Belega have been able to understand the basic concepts of parents' professions and even tell stories about the professions of their parents and the people around them. The approach of interesting visual images and storytelling is suitable for learning because it increases enthusiasm, active interaction, and interest in further exploration of children.