George Nousias, Konstantinos K. Delibasis, Georgios Labiris
Blink detection is considered a useful indicator both for clinical conditions and drowsiness state. In this work, we propose and compare deep learning architectures for the task of detecting blinks in video frame sequences. The first step is the training and application of an eye detector that extracts the eye regions from each video frame. The cropped eye regions are organized as three-dimensional (3D) input with the third dimension spanning time of 300 ms. Two different 3D convolutional neural networks are utilized (a simple 3D CNN and 3D ResNet), as well as a 3D autoencoder combined with a classifier coupled to the latent space. Finally, we propose the usage of a frame prediction accumulator combined with morphological processing and watershed segmentation to detect blinks and determine their start and stop frame in previously unseen videos. The proposed framework was trained on ten (9) different participants and tested on five (8) different ones, with a total of 162,400 frames and 1172 blinks for each eye. The start and end frame of each blink in the dataset has been annotate by specialized ophthalmologist. Quantitative comparison with state-of-the-art blink detection methodologies provide favorable results for the proposed neural architectures coupled with the prediction accumulator, with the 3D ResNet being the best as well as the fastest performer.
Photography, Computer applications to medicine. Medical informatics
In electrocardiograms (ECGs), multiple forms of encryption and preservation formats create difficulties for data sharing and retrospective disease analysis. Additionally, photography and storage using mobile devices are convenient, but the images acquired contain different noise interferences. To address this problem, a suite of novel methodologies was proposed for converting paper-recorded ECGs into digital data. Firstly, this study ingeniously removed gridlines by utilizing the Hue Saturation Value (HSV) spatial properties of ECGs. Moreover, this study introduced an innovative adaptive local thresholding method with high robustness for foreground–background separation. Subsequently, an algorithm for the automatic recognition of calibration square waves was proposed to ensure consistency in amplitude, rather than solely in shape, for digital signals. The original signal reconstruction algorithm was validated with the MIT–BIH and PTB databases by comparing the difference between the reconstructed and the original signals. Moreover, the mean of the Pearson correlation coefficient was 0.97 and 0.98, respectively, while the mean absolute errors were 0.324 and 0.241, respectively. The method proposed in this study converts paper-recorded ECGs into a digital format, enabling direct analysis using software. Automated techniques for acquiring and restoring ECG reference voltages enhance the reconstruction accuracy. This innovative approach facilitates data storage, medical communication, and remote ECG analysis, and minimizes errors in remote diagnosis.
This research introduces a cutting-edge approach to traffic infrastructure digitization, integrating UAV oblique photography with LiDAR point clouds for high-precision, lightweight 3D road modeling. The proposed method addresses the challenge of accurately capturing the current state of infrastructure while minimizing redundancy and optimizing computational efficiency. A key innovation is the development of the TJYRoad-Net model, which achieves over 85% mIoU segmentation accuracy by including a traffic feature computing (TFC) module composed of three critical components: the Regional Coordinate Encoder (RCE), the Context-Aware Aggregation Unit (CAU), and the Hierarchical Expansion Block. Comparative analysis segments the point clouds into road and non-road categories, achieving centimeter-level registration accuracy with RANSAC and ICP. Two lightweight surface reconstruction techniques are implemented: (1) algorithmic reconstruction, which delivers a 6.3 mm elevation error at 95% confidence in complex intersections, and (2) template matching, which replaces road markings, poles, and vegetation using bounding boxes. These methods ensure accurate results with minimal memory overhead. The optimized 3D models have been successfully applied in driving simulation and traffic flow analysis, providing a practical and scalable solution for real-world infrastructure modeling and analysis. These applications demonstrate the versatility and efficiency of the proposed methods in modern traffic system simulations.
The ever-growing global population, combined with the industrial revolution and increased consumerism, has led to an exponential surge in waste generation. The implementation of integrated solid waste management (ISWM) is crucial for addressing the challenges posed by increasing waste generation and limited landfill space. Remote sensing (RS) and Geographic Information Systems (GIS) have emerged as powerful tools to support ISWM strategies through their diverse applications. This short review explores the novel applications of RS and GIS in ISWM and highlights their potential for enhancing waste management practices. RS techniques, such as satellite imagery and aerial photography, enable the accurate mapping and monitoring of waste generation, disposal sites, and recycling facilities. GIS facilitates spatial analysis and decision-making, allowing for optimized waste collection routes, landfill site selection, and the identification of suitable locations for waste-to-energy projects. Furthermore, RS and GIS provide valuable insights into waste composition analysis, landfill stability assessment, and environmental impact evaluation. This review underscores the importance of leveraging RS and GIS technologies to improve waste management practices and offers valuable recommendations for future research in this field.
The article is devoted to the study of the legal regulation of the use of technical means related to the implementation of video recording, photography and filming by subjects of public administration, in particular, those authorized to draw up protocols on administrative offenses by officials. The research is carried out on the basis of strict observance of human rights and freedoms, as fundamental principles of civil society and a democratic state, which should determine the powers, their use, and therefore the behavior of subjects of public administration during the use of technical means of videography, photography and filmmaking. It is argued that no socially significant goal may be the basis for limiting or depriving a person of his or her rights and freedoms, including the right to privacy, in any form. It is reasoned that the use of relevant technical means in administrative delict proceedings has a number of features and a number of imperatives, the violation of which leads to the inadmissibility of relevant evidence. In particular, it is emphasized that the installation of video surveillance systems in public (public) places must necessarily be accompanied by the installation of appropriate posters, informational signs indicating the implementation of video surveillance and the implementation of video recording, photography and filming, and therefore the preservation and accumulation of such information about person and the possibility of using it for the appropriate purposes and with the appropriate purpose.
It is obvious that any fixation of a person (static – for photography, dynamic – for video and film shooting, with or without sound recording) is a direct interference in a person’s private life. As a result, the use of appropriate means is possible only on the grounds provided for in the law. The key condition for photo and video recording of a person is to warn the person about the filming, which in turn involves giving the latter’s consent to such filming. The technical means used for such filming are of great importance, in particular, that the latter are certified, calibrated and have received appropriate permits, including sanitary and hygienic, for their use in Ukraine by subjects of public administration, or have been transferred for use to specific officials, as well as the right (they have undergone appropriate training) of the specified officials regarding behavior with such technical means, including the legal grounds for their use.
Law in general. Comparative and uniform law. Jurisprudence
Daryna Dementieva, Mikhail Kuimov, Alexander Panchenko
The rapid spread of deceptive information on the internet can have severe and irreparable consequences. As a result, it is important to develop technology that can detect fake news. Although significant progress has been made in this area, current methods are limited because they focus only on one language and do not incorporate multilingual information. In this work, we propose Multiverse—a new feature based on multilingual evidence that can be used for fake news detection and improve existing approaches. Our hypothesis that cross-lingual evidence can be used as a feature for fake news detection is supported by manual experiments based on a set of true (legit) and fake news. Furthermore, we compared our fake news classification system based on the proposed feature with several baselines on two multi-domain datasets of general-topic news and one fake COVID-19 news dataset, showing that (in combination with linguistic features) it yields significant improvements over the baseline models, bringing additional useful signals to the classifier.
Photography, Computer applications to medicine. Medical informatics
All The Sites (Todos Os Sítios) is an exercise of critical reflection on the contemporary landscape. It brings together a set of photographs, which constitute its body of visual documents, and a written argument that aims to inform the intentions and paradigms of the photographs. This article organizes this reflection through two moments: the first concerns the definition of the term site, based on a perception of the landscape as a cultural construction, an expression coined by WJT Mitchell, and the second, through the work of three photographers – Eugène Atget, Walker Evans and Guido Guidi, seeks to situate the visual paradigms of photographs of All the Sites and the discourse that is inherent to them.
Alexander Denker, Maximilian Schmidt, Johannes Leuschner
et al.
Over recent years, deep learning methods have become an increasingly popular choice for solving tasks from the field of inverse problems. Many of these new data-driven methods have produced impressive results, although most only give point estimates for the reconstruction. However, especially in the analysis of ill-posed inverse problems, the study of uncertainties is essential. In our work, we apply generative flow-based models based on invertible neural networks to two challenging medical imaging tasks, i.e., low-dose computed tomography and accelerated medical resonance imaging. We test different architectures of invertible neural networks and provide extensive ablation studies. In most applications, a standard Gaussian is used as the base distribution for a flow-based model. Our results show that the choice of a radial distribution can improve the quality of reconstructions.
Photography, Computer applications to medicine. Medical informatics
In the present paper I discuss the short story "ancinho" and the image that corresponds to a supplement, both integrating the work Catálogo de Perdas (2017), by João Anzanello Carrascoza and Juliana Monteiro Carrascoza, from some operators of intermediality studies (Hutcheon, 2013; Guadreault and Marion, 2012; Rajewsky, 2012). I present a summary description of the image composition, from some concepts of photography (Erhlich, 1986; Berger, 2017), as well as of the narratological elements of the short story (Genette, 2017; Franco Junior, 2009), in order to highlight aspects of the creative and interpretative transposition. Considering a paratextual/epitextual element (Genette, 2009), present at the end of the work, which operates as a kind of subtitle (Carrascoza, 2017) it is possible to hypothesize that the expression material of the adaptation - the different media -, corresponds to a media order of different modes of engagement - telling, showing and interacting (Hutcheon, 2013) and its meaning effects, such as memory and affects.
The article analyses and interprets Robert Stando’s little-known educational film Strach ma wielkie oczy [Fear has large eyes]. The film was made in 1965 and produced by the Documentary Film Studio in Warsaw. The author explores the original character of the film, reconstructing the stylistic and compositional techniques used by filmmakers, among others, in the field of cinematography (underwater photography), editing, word function, music, sound effects etc.
In high altitude regions, affected by the low-pressure and low-temperature atmosphere, diesel knock is likely to be encountered in heavy-duty engines operating at low-speed and high-load conditions. Pressure oscillations during diesel knock are commonly captured by pressure transducers, while there is a lack of direct evidence and visualization images, such that its fundamental formation mechanism is still unclear. In this study, optical experiments on diesel knock with destructive pressure oscillations were investigated in an optical rapid compression machine. High-speed direct photography and simultaneous pressure acquisition were synchronically performed, and different injection pressures and ambient pressures were considered. The results show that for the given ambient temperature and pressure, diesel knock becomes prevalent at higher injection pressures where fuel spray impingement becomes enhanced. Higher ambient pressure can reduce the tendency to diesel knock under critical conditions. For the given injection pressure satisfying knocking combustion, knock intensity is decreased as ambient pressure is increased. Further analysis of visualization images shows diesel knock is closely associated with the prolonged ignition delay time due to diesel spray impingement. High-frequency pressure oscillation is caused by the propagation of supersonic reaction-front originating from the second-stage autoignition of mixture. In addition, the oscillation frequencies are obtained through the fast Fourier transform (FFT) analysis.
Target object detection is an important research direction in the area of hyperspectral imaging (HSI) as it aims to detect the anomalies or objects in HSI. Some of the existing target object detection methods are merely suitable for HSI with low resolution as they failed to apply directly in the high‐resolution HSI. Therefore, an effective target detection method named chicken social‐based deep belief network (CS‐based DBN) is proposed to achieve an automatic target object detection framework in the high‐resolution HSI. The proposed CS‐based DBN is developed by integrating the chicken swarm optimisation with the social ski‐driver algorithm. The optimal solution for detecting the target object is revealed through the fitness function, which accepts the minimal error value as the best solution. Moreover, the weights of the DBN classifier are optimally trained based on the proposed algorithm to render an accurate and optimal solution in detecting the target objects. The proposed CS‐based DBN obtained better performance through the facility of stochastic exploration in search space. Moreover, the results achieved using the proposed model in terms of accuracy, specificity, and sensitivity are 0.8950, 0.8940, and 0.9, respectively.
The home is the ideal place for a domestic appropriation of space accompanied by delicately arranged layouts linked to daily existence and personal idiosyncrasies. Photographers have chosen to investigate these unstable and familiar environments. This is especially the case for François Hers (Intérieurs, 1981), Jean-Marc Tingaud (Intérieurs, 1991) or Hortense Soichet (Intérieurs. Logements à la Goutte d’Or, 2011). The first photographer takes middle distance shots with garish tones. The second uses close-ups to capture small-scale frail arrangements. The third associates shots of apartments with words from the inhabitants giving snippets of their life stories. The processes used by these photographers succeed in provoking a profound reflection on the vernacular arrangements of these interior spaces, where often inexpensive mass-produced objects are organised in an individual and changing syntax, linked to the “arts of making” of their inhabitants.
In the recent decade, chaos‐based image encryption algorithms gained attention due to their pros and cons. The authors suggest one such algorithm of image encryption for different colour space using feed forward initial condition to pursue random permutation by combining 1D logistic map with a series of tent maps. The algorithm adds one more novel step to protect and encrypt binary image by concealing it within a cover grey image using bit‐plane decomposition methods. Sensitivity towards initial condition is shown using block division of image by applying a stream of random initial conditions to each block for encryption along with XOR operation which leads the key space high (≃2484). For better performance analysis, the proposed scheme has been tested with many colour space images including a binary image. The proposed technique is more efficient with respect to time complexity and resistance to vulnerability aspects.
A large-scale perpendicular cavitating vortices (PCVs), at the trailing edge of attached cavitation on the blade suction side near the tip region, has been found recently due to the great impact on performance breakdown in an axial waterjet pump. However, the trajectory and dynamics of this structure have been given scant attention. In this study, some visualized experiments were carried out to elucidate the PCVs for different conditions. The high-speed imaging coupled with numerical computations show that the vortical cloud cavitation is induced by the combination of tip leakage vortex (TLV) and radial re-entrant jets from the hub to blade tip. Moreover, the trajectory and intensity of PCVs depend on the operating conditions strongly, whether the other parameters, e.g. blade number and blade geometries, are modified. When taken the blade number into consideration, as a consequence of flow passage width and blade loading distributions, the dynamics and strength of PCVs vary considerably. Furthermore, an optimum clearance geometry is seen to eliminate corner vortex and clearance cavitation when the clearance edge is rounded on the pressure side. However, the more intensive tip leakage vortex cavitation is observed due to the increased amount of leakage flux. Additionally, in the original blade with sharp edges, the PCVs is relative weak and has a loose structure, resulting in the multiple interaction with the next blade. These phenomenon are responsible for the severe performance degradation and flow instabilities in the tip region of an axial-flow pump.
Drama – stage – actor
The author discusses the issue of acting and theatrical stage in the context of Józef Tischner’s philosophy, which sees the stage as the platform for freedom, and the meeting and parting of people, as well as their relationship with the Absolute. The language of the character is created by: the actor, screenplay, costumes, lighting and music. He introduces the idea of objectifying the stage and familiarising onself with role, the basis of which are relations between the plays characters.
Observing a century of relations between architecture and photography in the use of graphic, drawing and photographic practices, this paper follows some conceptual transactions between the two disciplines. Primarily, there is an essential difference however; in a given situation, photographers will seek to capture what is, whereas architects often work to formulate what can be. Over time, there has been a convergence of thinking and practice between the two disciplines, notably on the part of architects such as Neil Denari whose thinking reflects certain practices of photographers like Andreas Gursky and Jeff Wall. In examining these occurrences, it is relevant to note Roland Barthes' critical insight of the binary pair he called the studium and punctum to visualize a cohesive overall background coupled with a specific element occurring in photography, and by inference, in architecture, especially at the conceptual and representational moment.
Terrestrial Laser Scanning (TLS), 3-D modeling and its Web visualization are the three key steps needed to perform storage and
grant-free and wide access to cultural heritage, as highlighted in many recent examples. The goal of this study is to set up 3-D Web
resources for "virtually" visiting the exterior of the <i>Abbaye de l'Epau</i>, an old French abbey which has both a rich history and
delicate architecture. The virtuality is considered in two ways: the flowing navigation in a virtual reality environment around the
abbey and a game activity using augmented reality. First of all, the data acquisition consists in GPS and tacheometry survey,
terrestrial laser scanning and photography acquisition. After data pre-processing, the meshed and textured 3-D model is generated
using 3-D Reshaper commercial software. The virtual reality visit and augmented reality animation are then created using Unity
software. This work shows the interest of such tools in bringing out the regional cultural heritage and making it attractive to the
public.
Mir Hadi Aziz Jalali, Alireza Faghihi, Hossein Eshghi
Background: Topical flocinolone acetonide and tacrolimus have been used to treat vitiligo for a long time, but there is not enough data available to conduct management decision for these patients. Tacrolimus and corticosteroid have been used for head and neck lesions successfully, and have been accepted as standard treatment. The present study is designed to compare the therapeutic effects of flocinolone acetonide and tacrolimus with each other and with the placebo in the treatment of vitiligo lesions of upper extremities.
Methods: The current study was carried out on 28 patients of 16-53 years of age with 150 depigmented lesions of upper extremities. The lesions ranged from 3 to 6 cm. 50 lesions were treated with flocinolone acetonide in isopropyl alcohol (50 grams in 50 cc), 50 lesions with tacrolimus, and 50 control lesions with placebo. Patients were followed for 6 months and visited at 2, 4 and 6 months. Disease response was evaluated by approach of clinical criteria. We considered complete or partial repigmentation as the most important clinical criteria. No systemic treatment or phototherapy was used in this study. Moreover, patients were assessed for any possible drug side- effects. Standard photography was applied in order to follow any changes in lesions. The repigmentation achieved for each group and at each follow-up visit were analyzed and compared to the other groups.
Findings: The response rate for the tacrolimus group was: 5 lesions showed complete response, 10 lesions showed partial repigmentation, 3 patches worsened, and 32 showed no alteration. In the flocinolone group 8 lesions had complete response, 24 lesions showed repigmentation, 3 lesions showed partial repigmentation, 3 lesions worsened, and 40 lesions showed no alteration. In the placebo group 1 lesion showed complete response, 3 showed partial response, 6 lesions worsened, and 40 showed no alteration. In our study the response rate of both flocinolone acetonide and tacrolimus groups showed a significant difference to the placebo group (P = 0.049 and P = 0.034, respectively), but no significant difference was observed between the two groups (P = 0.67).
Conclusion: Topical flocinolone acetonide and tacrolimus showed no significant differences in the treatment of vitiligo Lesions; therefore, further studies are needed for treatment guidelines.