Hasil untuk "Photography"

A. Sommer, J. Katz, H. Quigley et al.

Matteo Kolyszko, Marco Buzzelli, Simone Bianco et al.

Hyperspectral imaging (HSI) enables fine spectral analysis but is often limited by low spatial resolution due to sensor constraints. To address this, we propose CGNet, a color-guided hyperspectral super-resolution network that leverages complementary information from low-resolution hyperspectral inputs and high-resolution RGB images. CGNet adopts a dual-encoder design: the RGB encoder extracts hierarchical spatial features, while the HSI encoder progressively upsamples spectral features. A multi-scale fusion decoder then combines both modalities in a coarse-to-fine manner to reconstruct the high-resolution HSI. Training is driven by a hybrid loss that balances L1 and Spectral Angle Mapper (SAM), which ablation studies confirm as the most effective formulation. Experiments on two benchmarks, ARAD1K and StereoMSI, at <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>×</mo><mn>4</mn></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>×</mo><mn>6</mn></mrow></semantics></math></inline-formula> upscaling factors demonstrate that CGNet consistently outperforms state-of-the-art baselines. CGNet achieves higher PSNR and SSIM, lower SAM, and reduced <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>Δ</mo><msub><mi>E</mi><mn>00</mn></msub></mrow></semantics></math></inline-formula>, confirming its ability to recover sharp spatial structures while preserving spectral fidelity.

Nerida Woodhams Bertozzi

In Silenzio. Le sette vite di Diana Karenne by Melania Mazzucco, it becomes clear from the outset that photography, silent film and narrative mechanisms related to the visual, play a structuring role in the novel. The present article examines the forms of hybrid textuality (such as the iconotext) and the various instances of ekphrasis and cinematographic ekphrasis present in the text. The analysis of these formal elements allows for a parallel to be traced between cinematographic ekphrasis and the biographical mode in narrative fiction: just as the literary text reconjures the silent images of cinema through language and the written text, so too does the author, when faced with the silence and impossibility of accessing the past, intervene through fiction to recreate a life. In Silenzio, it is through ekphrasis and cinematic ekphrasis that the gestural narrative language of silent film can emerge, the embodied narrative language characteristic of this medium, creating a space of intersemiotic exchange in which questions relating to agency and (in)visibility in the biographical novel are raised.

Ahuja AS, Paredes III AA, Eisel MLS et al.

Abhimanyu S Ahuja,1,&amp;ast; Alfredo A Paredes III,2,&amp;ast; Mallory LS Eisel,3,&amp;ast; Cole Miller,4 Nina Truong,3 Julie Falardeau1 1Department of Ophthalmology, Casey Eye Institute, Oregon Health and Science University, Portland, OR, USA; 2Charles E. Schmidt College of Medicine, Florida Atlantic University, Boca Raton, FL, USA; 3College of Medicine, Florida State University, Tallahassee, FL, USA; 4Leonard M. Miller School of Medicine, University of Miami, Miami, FL, USA&amp;ast;These authors contributed equally to this workCorrespondence: Abhimanyu S Ahuja, Department of Ophthalmology, Casey Eye Institute, Oregon Health and Science University, 515 SW Campus Drive, Portland, OR, 97239, USA, Email ahujaa@ohsu.edu Julie Falardeau, Department of Ophthalmology, Casey Eye Institute, Oregon Health and Science University, 515 SW Campus Drive, Portland, OR, 97239, USA, Email falardea@ohsu.eduAbstract: Artificial intelligence (AI) is rapidly reshaping neuro-ophthalmic care by extracting clinically significant information from imaging, biomarkers, and patient-level clinical data. We review recent advances across neurodegenerative disease detection using retinal biomarkers, automated recognition of optic disc swelling and its mimics, glaucoma screening and quantification, and classification of hereditary optic neuropathies. Using fundus photography and optical coherence tomography (OCT), contemporary machine learning (ML) systems, including deep learning as well as other supervised learning models, report strong discrimination for papilledema versus pseudopapilledema, non-arteritic anterior ischemic optic neuropathy (NAION) against similar presenting entities, and glaucomatous damage including indirect estimation of retinal nerve fiber layer (RNFL) thickness. Early work also suggests that retinal features can aid detection of mild cognitive impairment (MCI) and major neurocognitive disease. However, despite promising results, most studies remain retrospective and single-center, while focusing on imaging-only, limiting generalizability and clinical interpretability. Therefore a variety of challenges related to dataset heterogeneity, overfitting, limited external validation, and the gap between high diagnostic accuracy and practical clinical utility remain unresolved. Future prospective, multicenter evaluations focusing on integrating multimodal clinical data through explainable AI systems are necessary to improve diagnostic consistency, shorten time to care, and expand access for underserved populations.Keywords: artificial intelligence, neuro-ophthalmology, deep learning, machine learning, support vector machine, extreme learning machine

Ciliang Shao, Ruijin Xue, Lixu Gu

Accurate registration of MRI and TRUS images is crucial for effective prostate cancer diagnosis and biopsy guidance, yet modality differences and non-rigid deformations pose significant challenges, especially in dynamic imaging. This study presents a novel cross-modal MRI-TRUS registration framework, leveraging a dual-encoder architecture with an Enhanced Cross-Modal Channel Attention (E-CMCA) module and a LSTM-Based Spatial Deformation Modeling Module. The E-CMCA module efficiently extracts and integrates multi-scale cross-modal features, while the LSTM-Based Spatial Deformation Modeling Module models temporal dynamics by processing depth-sliced 3D deformation fields as sequential data. A VecInt operation ensures smooth, diffeomorphic transformations, and a FuseConv layer enhances feature integration for precise alignment. Experiments on the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>μ</mi></semantics></math></inline-formula>-RegPro dataset from the MICCAI 2023 Challenge demonstrate that our model significantly improves registration accuracy and performs robustly in both static 3D and dynamic 4D registration tasks. Experiments on the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>μ</mi></semantics></math></inline-formula>-RegPro dataset from the MICCAI 2023 Challenge demonstrate that our model achieves a DSC of 0.865, RDSC of 0.898, TRE of 2.278 mm, and RTRE of 1.293, surpassing state-of-the-art methods and performing robustly in both static 3D and dynamic 4D registration tasks.

Sean S. Healy, Carl N. Stephan

When an unidentified skeleton is discovered, a video superimposition (VS) of the skull and a facial photograph may be undertaken to assist identification. In the first instance, the method is fundamentally a photographic one, requiring the overlay of two 2D photographic images at transparency for comparison. Presently, mathematical and anatomical techniques used to compare skull/face anatomy dominate superimposition discussions, however, little attention has been paid to the equally fundamental photographic prerequisites that underpin these methods. This predisposes error, as the optical parameters of the two comparison photographs are (presently) rarely matched prior to, or for, comparison. In this paper, we: (1) review the basic but critical photographic prerequisites that apply to VS; (2) propose a replacement for the current anatomy-centric searches for the correct ‘skull pose’ with a photographic-centric camera vantage point search; and (3) demarcate superimposition as a clear two-stage phased procedure that depends first on photographic parameter matching, as a prerequisite to undertaking any anatomical comparison(s).

Wojciech Sternak

In the text, I discuss the problems of the genocide experience in the context of mass tourism. I point out that large-scale Holocaust memorials and genocide museums incorporated into the mass-tourism industry are drowning out cries of remembrance. I propose three categories of commemoration: “Captions”, “Monuments” and “Stand-alone Works”. The latter category includes fine art photography among others. Using the case of the photographic series Koenigsgraben, I point out that the category of “Stand-alone Works” seems to have the greatest potential (next to historical enviro mental activeness) to free the cry of remembrance from beneath the concrete of the monuments.

Donato Antonio Raele, Maria Assunta Cafiero

<i>Rickettsia aeschlimannii</i> infection is an emerging human tick-borne disease with only a few recorded cases. We reported a presumable autochthonous case of rickettsiosis in an Italian cattle breeder associated with a <i>Hyalomma marginatum</i> bite. <i>Rickettsia aeschlimannii</i> DNA was detected in both the tick specimen from the patient and the grazing cattle close to his farm.

Jun Tang, Yanjiang Wang, Sichao Fu et al.

Abstract Skeleton‐based action recognition is an inspired yet challenging task in computer vision. Recently, the latest graph convolutional network (GCN), which generalises well‐established convolutional neural networks to non‐Euclidean structures, is proven to be highly successful for action recognition from body skeleton data. However, the GCN architecture has not been fully studied. In this work, a Fisher vector (FV) encoding based GCN architecture (FV‐GCN) is proposed, which exceeds the limitations of existing GCN‐based methods by combining the GCN model with FV encoding. A channel‐wise spatial–temporal aggregation function to preserve spatial–temporal information in the whole action clip and integrate it into the FV‐GCN architecture is also presented. Since FV is different from the GCN structure, this hybrid architecture that incorporates the advantages of both algorithms can discover complementary information of feature representation effectively. On two challenging human action datasets, kinetics, and NTU‐RGBD, improved performance is demonstrated over the baseline method, and the FV‐GCN is better or comparable to some state‐of‐the‐art methods.

Lucija Furač

How can photography inform poetic language? Molly Thomasy Blasing, an associate professor of Russian studies at the University of Kentucky (USA) who specialises in modern and contemporary Russian poetry as well as encounters between literature and the visual arts, tries to answer this question in her book Snapshots of the Soul: Photo-Poetic Encounters in Modern Russian Culture.

P. Gunasekhar, S. Vijayalakshmi

Abstract Liver cancer is the major reason for death in this entire world. Manual detection of cancer tissue is found time consuming and difficult. Therefore, the development of an automatic detection approach with high accuracy for liver cancer is considered as the main aim of this work. The image processing approach can use the CAD for the classification of liver cancer in order to assist the physician in the decision‐making process. An automated approach to effective classification of the liver tumour using effective features is conveyed in terms of the CAD system. Traditionally, radiologists delineate the liver and liver lesion on a slice‐by‐slice basis, which is time consuming and susceptible to inter‐ and intra‐rater variations. Automatic methods for the segmentation of liver and liver tumours are, thus, highly demanded in clinical practice. A systematic review is being carried out to detect reported liver cancer from 2013 to 2020. Finally, a more precise technical direction is provided for all researchers in this review. Research gaps for earlier detection and its potential future aspects are also discussed.

Niki Evelpidou, Alexandros Petropoulos, Anna Karkani et al.

Coastal lagoons and dunes are of great ecological importance, not only for providing habitats for rare flora and fauna, but also for protecting coastal areas from rising sea levels and storms, etc. Even though these features are unique for sustainable development and are extremely important to the natural environment and economy, they are one of the most vulnerable and threatened ecosystems due to their small size. The western coasts of Naxos (central Aegean Sea) represent an example of such phenomena, with various wetlands bordered by low-lying sand dunes. The aim of our study is to assess the vulnerability and pressures of the western coasts of Naxos Isl. by taking into consideration both natural and anthropogenic factors. We used a variety of approaches for the environmental and geomorphological study of the coastal zone to achieve this goal, including: (a) study of aerial photography from 1960 until today, (b) systematic seasonal aerial monitoring by drone, since 2015, (c) use of DGPS for the mapping of the coastal zone and for obtaining detailed topographic sections, and (d) dune mapping. Our findings reveal the vulnerability of the western coasts of Naxos due to sea level rise, tectonic subsidence, and a variety of anthropogenic pressures, such as uncontrolled parking, vegetation uprooting, sand extractions, and heavy touristic traffic. Therefore, the protection of the sand dunes, their restoration where they have been eroded, the definition of a zone of control, and restriction of human activities must be a key priority.

Václav Řeřicha, Libor Práger

Each technology amplifies human functions, with photographs and videos enhancing vision and memory. The appeal of photography results from the fact that the stationary single eye is technologically extended. The technology of photography exceeds the limits of the eye, as the camera is a total stationary light catcher without the blurred edges of human vision. Photographs are “magical” and  appealing because they suddenly offer an improved eye, another more powerful and extended recorder of visual events for eternity outside our memory. Recorded events are felt to have more reality than the original, while a photograph as an experience translated into a new medium “bestows a delightful playback of earlier awareness.”1 These are therefore ideal means of communication for the platforms of the digital environment of social media and esports. The rapid development of digital photography has had the effect of returning the user to the content of historical technologies, with video clips flipping back to mediaeval performances, social media communicating with images and symbols of the non-literacy environment of the Middle Ages, and 3D imaging flipping back to sculpting. Non-print perceptual learning is becoming more prevalent, with literate cultures rendered obsolete by the inclusive and instantaneous digital environment.

Ibrahem Kandel, Mauro Castelli, Aleš Popovič

The classification of the musculoskeletal images can be very challenging, mostly when it is being done in the emergency room, where a decision must be made rapidly. The computer vision domain has gained increasing attention in recent years, due to its achievements in image classification. The convolutional neural network (CNN) is one of the latest computer vision algorithms that achieved state-of-the-art results. A CNN requires an enormous number of images to be adequately trained, and these are always scarce in the medical field. Transfer learning is a technique that is being used to train the CNN by using fewer images. In this paper, we study the appropriate method to classify musculoskeletal images by transfer learning and by training from scratch. We applied six state-of-the-art architectures and compared their performance with transfer learning and with a network trained from scratch. From our results, transfer learning did increase the model performance significantly, and, additionally, it made the model less prone to overfitting.

Zhichao Li, Yilin Li, Wanchun Lu et al.

From the perspective of platform economics, crowdsourcing is a very efficient business model, and the pricing of crowdsourcing tasks is a key factor for the sustainable development of the crowdsourcing model. In the logistics industry, crowdsourcing provides a new idea of sustainable development for logistics enterprises, and reasonable distribution pricing is the key to achieving sustainable development. This paper innovatively adds dynamic and decentralized characteristics of logistics on the basis of a detailed analysis of pricing methods and uses this as a basis to build a pricing model. First, based on existing crowdsourced photography task pricing data, this paper establishes a project-centric domain and builds metrics into the attributes of each project based on the data in that domain. Then, a regression model is used to fit the completion rate of previous projects, and a multiple linear regression and optimal pricing mechanism are established. Finally, the DBSCAN algorithm is used to cluster areas with a high project density, and a pricing optimization model based on polynomial Logit (MNL) is established. We found through the model analysis that the optimized pricing strategy of crowdsourcing logistics services has a better packaging completion rate based on a combination of complex factors including bundling and outliers. In short, the main contributions of this paper are to build a complex mathematical model for crowdsourcing tasks, improve the algorithmic deficiencies of the previous crowdsourcing task pricing methods, and provide a reference for further research on crowdsourcing tasks.

Feng Liu, Mingming Xu, Tongfeng He

Amina Kharbach, Benaissa Bellach, Mohammed Rahmoune et al.

In medical image processing, evaluating the variations of lesion volume plays a major role in many medical applications. It helps radiologists to follow-up with patients and examine the effects of therapy. Several approaches have been proposed to meet with medical expectations. The present work comes within this context. We present a new approach based on the local dissimilarity volume (LDV) that is a 3D representation of the local dissimilarity map (LDM). This map presents a useful means to compare two images, offering a localization of information. We proved the effectiveness of this method (LDV) compared to medical techniques used by radiologists. The result of simulations shows that we can quantify lesion volume by using the LDV method, which is an efficient way to calculate and localize the volume variation of anomalies. It allowed a time savings with the compete satisfaction of an expert during the medical treatment.

Angela Schuster, Marlene Thielecke, Vaomalala Raharimanga et al.

Abstract Background Tungiasis is highly prevalent in low- and middle-income countries but remains often under diagnosed and untreated eventually leading to chronic sequels. The objective of the study was to assess whether tungiasis-associated inflammation can be detected and quantified by high-resolution infrared thermography (HRIT) and whether after removal of the parasite inflammation resolves rapidly. Methods Patients with tungiasis were identified through active case finding. Clinical examination, staging, and thermal imaging as well as conventional photography were performed. In exemplary cases, the embedded sandfly was extracted and regression of inflammation was assessed by thermal imaging 4 days after extraction. Results The median perilesional temperature was significantly higher than the median temperature of the affected foot (rho = 0.480, p = 0.003). Median perilesional temperature measured by high-resolution infrared thermography was positively associated with the degree of pain (rho = 0.395, p < 0.017) and semi-quantitative scores for acute (rho = 0.380, p < 0.022) and chronic (rho = 0.337, p < 0.044) clinical pathology. Four days after surgical extraction, inflammation and hyperthermia of the affected area regressed significantly (rho = 0.457, p = 0.005). In single cases, when clinical examination was difficult, lesions were identified through HRIT. Conclusion We proved that HRIT is a useful tool to assess tungiasis-associated morbidity as well as regression of clinical pathology after treatment. Additionally, HRIT might help to diagnose hidden and atypical manifestations of tungiasis. Our findings, although still preliminary, suggest that HRIT could be used for a range of infectious skin diseases prevalent in the tropics. Trial registration ISRCTN11415557 , Registration date: 13 July 2011.

Pablo Porciúncula

Concebir reportajes fotográficos en soportes multimedia plantea nuevos desafíos para los fotógrafos. Hay que aprehender nuevos lenguajes y formarse en ellos. Es necesario incursionar en el mundo audiovisual y, sobre todo, mantener en la fotografía la esencia de la narración. Palabras clave: fotografía, reportajes, soportes multimedia. Conceiving multimedia photo reports poses new challenges for photographers. New languages must be apprehended and learnt. It is necessary to venture into the audiovisual world and, above all, maintaining the essence of story-telling in photography. Key words: photography, reports, multimedia.

Justyna Czaja

Warsaw - a city that does not exist The subject of the article is attempts in cinema and comics to reconstruct the image of pre-warWarsaw. The use of archival photographs of the capital, old postcards, and computer reconstructions using 3D technology increase the realism of the presentation, and provide the effect of intuition, intimacy, and directness. AWarsawnon-existent today comes to life again on the screen and in the pages of the comic book.