Hasil untuk "Photography"

Chisom E. Ogbuanya

The purpose of this research is to develop a multimodal medical image fusion method that will provide high-performance fusion images at a speed high enough for efficient real-time image-guided surgeries. This paper therefore proposes an improved multi-objective Darwinian particle swarm optimization method that incorporates a fractional calculus operator for effective multimodal medical image fusion. This is because multimodal medical image fusion is essential in many clinical diagnoses, and it represents a multi-objective problem due to the important objective indicators for measuring its efficiencies, such as the parameters of the neural network and the speed of the fusion process. The proposed method aims to optimize the Tsallis cross-entropy as a stimulating input to the pulse-coupled neural network (PCNN) for multimodal image fusion. In this work, multi-objective Darwinian particle swarm optimization (MODPSO) is utilized due to its ability to escape local optima more effectively than classical multi-objective particle swarm optimization (MOPSO). The approach uses the fact that the convergence rate of MODPSO is improved by introducing a fractional calculus operator, which is incorporated into the updating formulas for the velocity and position of the particles. The PCNN output serves as an optimal parameter for fusing the high-frequency coefficients of decomposed source images, which are initially decomposed into low- and high-frequency subbands. The low-frequency coefficients are fused using an averaging method. Results obtained in this paper show that the proposed method yields the highest average accuracy of 90.7% after a three-fold cross-validation was carried out with a small dataset extracted from a larger available dataset. In conclusion, the experimental results demonstrate the superiority of the proposed method over comparative methods in terms of both visual quality and quantitative evaluation.

Yange Sun, Sen Chen, Huaping Guo et al.

Skin lesion segmentation has achieved notable progress in recent years; however, accurate delineation remains challenging due to complex backgrounds, ambiguous boundaries, and low lesion-to-skin contrast. To address these issues, we propose the lesion-aware triple-path feature fusion network (LTPNet), an end-to-end framework that progressively processes features through extraction, refinement, and aggregation stages. In the extraction stage, we incorporate a general foreground–background attention to suppress background interference and accelerate model convergence. In the refinement stage, we introduce an attentive spatial modulator (ASM) to jointly exploit local structural cues and global semantic context for precise spatial modulation. We further develop a lesion-aware lite-gate attention (LALGA) module that performs local spatial feature modulation and global channel recalibration tailored to lesion characteristics. In the aggregation stage, we propose a triple-path feature fusion (TPFF) module that explicitly models feature relationships across scales via three complementary pathways: a common path (CP) for semantic consistency, a saliency path (SP) for highlighting co-activated regions, and a difference path (DP) for accentuating structural discrepancies. Extensive experiments on in-domain and cross-domain datasets show that LTPNet achieves superior segmentation accuracy with reasonable inference efficiency and model complexity, demonstrating its potential for efficient and reliable clinical decision support.

Fayuan Yan, Enzhi Wang, Xiaoli Liu et al.

Abstract A kind of slow deformation wave is produced in the crust under the action of internal and external factors, which plays an important role in the formation and occurrence of earthquakes. In this paper, uniaxial compression tests are carried out on red sandstone samples with uniform texture. Displacement controlled loading methods are adopted, and the loading rates are 0.1 mm/min, 0.5 mm/min and 1.0 mm/min, respectively. The micro-characterization method of speckle photography and DIC processing technology are adopted. The transfer characteristics of slow deformation and strain localization of red sandstone specimens during loading and deformation are discussed. The results show that the boundary advance velocity is proportional to the slow deformation transfer velocity with the change of position, so it can be considered that the slow deformation transfer velocity is equal to the particle motion transfer velocity. The formation and development of sample strain localization may be determined by the flow channel, nucleation and Luders zone evolution. The formation of the Luders band is related to the maximum value of the flow channel, and as deformation increases, the Luders band merges and develops with the maximum value of the nearby flow channel. By applying different loading rates, the influence of loading rate on the average transfer velocity of slow deformation was obtained; the slow deformation wave during seismic migration has similar characteristics to the deformation transfer in the experiment, therefore the research results have reference significance for further studies on the evolution characteristics of slow deformation waves and seismic migration.

Zhaoyu Shou, Yanjun Lin, Jianwen Mo et al.

The complexity of various factors influencing online learning makes it difficult to characterize learning concentration, while Accurately estimating students’ gaze points during learning video sessions represents a critical scientific challenge in assessing and enhancing the attentiveness of online learners. However, current appearance-based gaze estimation models lack a focus on extracting essential features and fail to effectively model the spatio-temporal relationships among the head, face, and eye regions, which limits their ability to achieve lower angular errors. This paper proposes an appearance-based gaze estimation model (RSP-MCGaze). The model constructs a feature extraction backbone network for gaze estimation (ResNetSC) by integrating ResNet and SCConv; this integration enhances the model’s ability to extract important features while reducing spatial and channel redundancy. Based on the ResNetSC backbone, the method for video gaze estimation was further optimized by jointly locating the head, eyes, and face. The experimental results demonstrate that our model achieves significantly higher performance compared to existing baseline models on public datasets, thereby fully confirming the superiority of our method in the gaze estimation task. The model achieves a detection error of 9.86 on the Gaze360 dataset and a detection error of 7.11 on the detectable face subset of Gaze360.

Jean Hunleth, Sienna Ruiz

Images are increasingly used in health research as a complement to discursive methods, to elicit more and different types of knowledge and experience from participants. The use of image-based research, such as drawing and photography, then, holds promises for understanding health in new ways. However, such promises fall short when researchers and audiences treat images as realist representations of participants’ lives. Images are never clear representations of an objective reality- this is not their value either during or after research. In this photo essay, we show and discuss how we countered image positivism in the PHRAME study, Photographing Health by Rural Adolescents in the Midwest. The photos shown in this essay take viewers into our interviews in PHRAME and then out to our modes of audience engagement. Throughout, play served as a critical orientation and form of listening. We show this, first, through glimpses into our interviews, where we engaged in play that transformed meanings of photos taken by the young people. Then we show how we engaged public health, academic audiences, and popular audiences of the young people’s photos in play where audiences were invited to co-produce meaning through interactive activities, rather than reading to extract meaning from the photos. In conclusion, we suggest that play as a mode of research and exchange holds transformative potential, taking health research beyond the image positivism that has constrained the methodology to expand visions of what health is and might be.

Shaofan Wang, Yukun Liu, Yanfeng Sun et al.

Abstract Medical images exhibit multi‐granularity and high obscurity along boundaries. As representative work, the U‐Net and its variants exhibit two shortcomings on medical image segmentation: (a) they expand the range of reception fields by applying addition or concatenate operators to features with different reception fields, which disrupts the distribution of the essential feature of objects; (b) they utilize the downsampling or atrous convolution to characterize multi‐granular features of objects, which can obtain a large range of reception fields but leads to blur boundaries of objects. A Shuffling Atrous Convolutional U‐Net (SACNet) for circumventing those issues is proposed. The significant component of SACNet is the Shuffling Atrous Convolution (SAC) module, which fuses different atrous convolutional layers together by using a shuffle concatenate operation, so that the features from the same channel (which correspond to the same attribute of objects) are merged together. Besides the SAC modules, SACNet utilizes an EP module during the fine and medium levels to enhance the boundaries of objects, and utilizes a Transformer module during the coarse level to capture an overall correlation of pixels. Experiments on three medical image segmentation tasks: abdominal organ, cardiac, and skin lesion segmentation demonstrate that, SACNet outperforms several state‐of‐the‐art methods and facilitates easy transplant to other semantic segmentation tasks.

Jia‐Jun Zhao, Zhi‐Qiang Liu, Si‐Jia Xie et al.

Abstract This paper mainly conducts a comparative study of body posture action feature extraction and recognition in three‐dimensional (3D) space through motion capture technology and virtual reality technology. Firstly, this paper proposes a body posture feature extraction method in 3D space to obtain joint point data and conduct body posture feature extraction research. At the same time, this method is used for action recognition research, which solves the difficulty of traditional methods in 3D scene feature extraction and motion recognition. In addition, this paper proposes two action comparison methods in 3D space. One is a ‘distance threshold method’ that calculates the distance between bones in the form of joint points and bones, which can finally provide the effect of dynamic display of sliders; the other is the ‘feature plane method’ that calculates the detailed information based on different skeletal joint point planes, and finally provides a text display effect with detailed body posture difference values. Finally, combined with virtual reality technology, an application platform for body posture feature recognition and comparison is designed and implemented, which solves the problems of poor visualization effect and weak interaction of traditional methods.

Christine Deslaurier

In reflexive mode, this article re-examines the difficulties of producing photographic materials in a research project in the humanities and social sciences which took place in Burundi between 2018 and 2020. The author was co-lead in this programme, Suburbu (Subsistance urbaine et mobilisations du travail au Burundi, early 20th century-early 21st century), carried out at the Faculté des Lettres et Sciences Humaines of the university of Burundi in the framework of the support provided by the Institut de Recherche pour le Développement (“Jeune équipe associée à l’IRD”). In this text, she takes note of the setbacks that stood in the way of achieving initial aims of the project with regard to photography—in particular holding an exhibition—to investigate the oversights that caused them, and to examine the disciplinary, cultural and human impediments and stumbling blocks that limited the range of possibilities in terms of taking photographs and the uses of photography for scientific purposes. The aim is to describe the practical situations as well as the theoretical negligence and technical lacks that caused the difficulties, and to highlight their impact, starting with the photographs taken by the team, in particular, and taking into account the expectations of what might have “made a good photo” for a public exhibition, and beyond that, for research and its heuristics.The text does not elude the succession of errors and the impression of levity that can be seen with hindsight regarding the (non-)use of photography in the Suburbu project. If certain of these anomalies are understandable and justifiable, for example the self-censorship that a hostile security situation obliged the team to practise, or ignorance of certain basic techniques for producing pictures that would be usable for scientific or aesthetic purposes, others are less so and can be put down to carelessness or amateurism that the author endeavours to examine. The expectations and the value of the rapprochement between the social sciences and photography had not really been thought through in advance, nor had the corpus of knowledge been consulted. Similarly, subjective reticence or objections bolstered a certain detachment with regard to photographs, considered as mere accessories or even of no use. Between the two, photographs were nonetheless taken, which “could have been good ones” if only their very low resolution had not made them unusable (a few examples are shown in this text). This last point, along with other failings of competence, have led the author to review the benefits, technical and practical, or intellectual and scientific, to be derived from collaboration between researchers and professional or experienced photographers. Finally, the idea is to encourage the teams to envisage the use of photography more routinely in humanities and social sciences projects by including professional photographers right from the preparatory stages or at the very least planning appropriate training courses.

XianBen Yang, Wei Zhang

Abstract Facial target detection is an important task in computer vision. Because heterogeneous face detection shows broad prospects, it has attracted extensive attention from the academic community. In recent years, with the rise of deep learning and its applications in computer vision, face detection technology has made great strides. This paper uses multi‐task cascaded convolutional neural network (MTCNN) for heterogeneous face feature detection. This algorithm makes full use of the advantages of image pyramid, boundary regression, fully convolutional attention networks and non‐maximum suppression. The main idea of this paper is to use candidate frame plus classifier for fast and efficient face detection. Specifically, the candidate window is generated by the proposal network (P‐Net), and the high‐precision candidate window is filtered and selected by the reduced network (R‐Net), and the final bounding box and facial key points are generated by the output network (O‐Net). In order to prove the effectiveness of this method in visible light, near‐infrared and sketch face recognition scenes, it was verified in the datasets of CUFS, CUFSF and CASIA NIR‐VIS 2.0. Experiments show that this method is effective for face images in heterogeneous face and is better than the latest algorithms.

M. Zhu, K. Zeng, G. Lin et al.

Abstract In clinical medicine, the segmentation of blood vessels in retinal images is essential for subsequent analysis in clinical diagnosis. However, retinal images are often noisy and their vascular structure is relatively tiny, which poses significant challenges for vessel segmentation. To improve the performance of vessel segmentation, an improved model IterNet++ based on the architecture of IterNet is proposed. First, curvelet signal analysis is applied to enhance retinal images. Second, residual convolution (ResConv) blocks and guided filters are introduced to utilise the encoder features of previous iterations in the model to reduce overfitting. Third, offline hard‐sample mining is used to improve segmentation performance by utilising training samples with low segmentation accuracy as many possible on a few‐sample training set. In addition, a test‐time augmentation method is applied to testing samples in test dataset during inference. Extensive experiments show that this model achieves Dice scores of 0.8313, 0.8277, and 0.8372 on DRIVE, CHASE‐DB1, and STARE datasets, respectively, demonstrating the best performance compared with IterNet and other baseline models.

Jitendra Madarkar, Poonam Sharma, Rimjhim Padam Singh

Abstract With the increasing use of surveillance cameras, face recognition is being studied by many researchers for security purposes. Although high accuracy has been achieved for frontal faces, the existing methods have shown poor performance for occluded and corrupt images. Recently, sparse representation based classification (SRC) has shown the state‐of‐the‐art result in face recognition on corrupt and occluded face images. Several researchers have developed extended SRC methods in the last decade. This paper mainly focuses on SRC and its extended methods of face recognition. SRC methods have been compared on the basis of five issues of face recognition such as linear variation, non‐linear variation, undersampled, pose variation, and low resolution. Detailed analysis of SRC methods for issues of face recognition have been discussed based on experimental results and execution time. Finally, the limitation of SRC methods have been listed to help the researchers to extend the work of existing methods to resolve the unsolved issues.

Alice Morin, Jens Ruchatz

This paper deals with photography in illustrated magazines and photobooks, and with what unfolds when photographs migrate from one media to the other. In such instances, we argue, reformatting is performed in distinctive affordances; yet such transfers also make visible the format conditions that underlie both the magazine and book media. By conducting an in-depth analysis of two exemplary photographs, by Horst P. Horst and Henri Cartier-Bresson, circulating between magazines and books, we aim to show how format markedly shapes photography in print and thus to demonstrate the work of format. In the process, matters of authoring and re-appropriating, as well as mechanisms of canonization and/or memorialization are brought to light. All contribute to structure and solidify the photographic field, as well as periodicals and books as media, in relationship to one another (and to their mediatic content). The established hierarchy of formats, in which photographs move up from magazines to books, in fact proved beneficial to both, bolstering the distinction – and thus the identity – of the media book and periodical.

Lauren Johnson

Seung Seog Han, Ik Jun Moon, Seong Hwan Kim et al.

<h4>Background</h4>The diagnostic performance of convolutional neural networks (CNNs) for diagnosing several types of skin neoplasms has been demonstrated as comparable with that of dermatologists using clinical photography. However, the generalizability should be demonstrated using a large-scale external dataset that includes most types of skin neoplasms. In this study, the performance of a neural network algorithm was compared with that of dermatologists in both real-world practice and experimental settings.<h4>Methods and findings</h4>To demonstrate generalizability, the skin cancer detection algorithm (https://rcnn.modelderm.com) developed in our previous study was used without modification. We conducted a retrospective study with all single lesion biopsied cases (43 disorders; 40,331 clinical images from 10,426 cases: 1,222 malignant cases and 9,204 benign cases); mean age (standard deviation [SD], 52.1 [18.3]; 4,701 men [45.1%]) were obtained from the Department of Dermatology, Severance Hospital in Seoul, Korea between January 1, 2008 and March 31, 2019. Using the external validation dataset, the predictions of the algorithm were compared with the clinical diagnoses of 65 attending physicians who had recorded the clinical diagnoses with thorough examinations in real-world practice. In addition, the results obtained by the algorithm for the data of randomly selected batches of 30 patients were compared with those obtained by 44 dermatologists in experimental settings; the dermatologists were only provided with multiple images of each lesion, without clinical information. With regard to the determination of malignancy, the area under the curve (AUC) achieved by the algorithm was 0.863 (95% confidence interval [CI] 0.852-0.875), when unprocessed clinical photographs were used. The sensitivity and specificity of the algorithm at the predefined high-specificity threshold were 62.7% (95% CI 59.9-65.1) and 90.0% (95% CI 89.4-90.6), respectively. Furthermore, the sensitivity and specificity of the first clinical impression of 65 attending physicians were 70.2% and 95.6%, respectively, which were superior to those of the algorithm (McNemar test; p < 0.0001). The positive and negative predictive values of the algorithm were 45.4% (CI 43.7-47.3) and 94.8% (CI 94.4-95.2), respectively, whereas those of the first clinical impression were 68.1% and 96.0%, respectively. In the reader test conducted using images corresponding to batches of 30 patients, the sensitivity and specificity of the algorithm at the predefined threshold were 66.9% (95% CI 57.7-76.0) and 87.4% (95% CI 82.5-92.2), respectively. Furthermore, the sensitivity and specificity derived from the first impression of 44 of the participants were 65.8% (95% CI 55.7-75.9) and 85.7% (95% CI 82.4-88.9), respectively, which are values comparable with those of the algorithm (Wilcoxon signed-rank test; p = 0.607 and 0.097). Limitations of this study include the exclusive use of high-quality clinical photographs taken in hospitals and the lack of ethnic diversity in the study population.<h4>Conclusions</h4>Our algorithm could diagnose skin tumors with nearly the same accuracy as a dermatologist when the diagnosis was performed solely with photographs. However, as a result of limited data relevancy, the performance was inferior to that of actual medical examination. To achieve more accurate predictive diagnoses, clinical information should be integrated with imaging information.

Chengzhang Zhong, Amy R. Reibman, Hansel A. Mina et al.

A majority of foodborne illnesses result from inappropriate food handling practices. One proven practice to reduce pathogens is to perform effective hand-hygiene before all stages of food handling. In this paper, we design a multi-camera system that uses video analytics to recognize hand-hygiene actions, with the goal of improving hand-hygiene effectiveness. Our proposed two-stage system processes untrimmed video from both egocentric and third-person cameras. In the first stage, a low-cost coarse classifier efficiently localizes the hand-hygiene period; in the second stage, more complex refinement classifiers recognize seven specific actions within the hand-hygiene period. We demonstrate that our two-stage system has significantly lower computational requirements without a loss of recognition accuracy. Specifically, the computationally complex refinement classifiers process less than 68% of the untrimmed videos, and we anticipate further computational gains in videos that contain a larger fraction of non-hygiene actions. Our results demonstrate that a carefully designed video action recognition system can play an important role in improving hand hygiene for food safety.

Aqsa Ajaz, Behzad Aliahmad, Himeesh Kumar et al.

Abstract Background Color fundus photography have been extensively used to explore the link between retinal morphology changes associated with various disease i.e. Diabetic Retinopathy, Glaucoma. The development of multimodal imaging system that integrates Infrared Scanning Laser Ophthalmoscope (IR-SLO) and Optical Coherence Tomography (OCT) could help in studying these diseases at an early stage. The aim of this study was to test the agreement between the retinal vasculature parameters from the Infrared images obtained from optical coherence tomography and color fundus imaging. Methods The IR and Color retinal images were obtained from 16 volunteer participants and seven retinal vessel parameters, i.e. Fractal Dimension (FD), Average Angle (ABA), Total Angle Count (TAC), Tortuosity (ST), Vessel/Background ratio (VBR), Central Retinal Arteriolar Equivalent (CRAE) and Central Retinal Venular Equivalent (CRVE) were extracted from these retinal images using Retinal Image Vasculature Assessment software (RIVAS) and Integrative Vessel Analysis (IVAN). Results The Bland Altman plot was used to investigate the agreement between the two modalities. The paired sample t-test was used to assess the presence of fixed bias and the slope of Least Square Regression (LSR) line for the presence of proportional bias. The paired sample t-test showed that there was no statistically significant difference between Color and IR based on retinal vessel features (all p values > 0.05). LSR also revealed no statistically significant difference in the retinal vessel features between Color and IR. Conclusion This study has revealed that there is a fair agreement between Color and IR images based on retinal vessel features. This research has shown that it is possible to use IR images of the retina to measure the retinal vasculature parameters which has the advantage of being flash-less, can be used even if there is opacity due to cataract, and can be performed along with OCT on the same device.

Dong Liang, Zhao Yuqi, Dai Cui et al.

In order to study the change rules of interior acoustic field with the development of cavitation, this article presented a method that through comparing the experiment results with numerical simulation results in cavitation bubbles’ distribution images under different cavitation coefficients to optimize the accuracy of acoustic field simulation using computational fluid dynamics combined with the Lighthill acoustic analogy. First, a closed visual testing system was established based on pump product test system and high-speed photography. Second, the cavitation performance under the rated operating condition was calculated using different cavitation models, in order to obtain both pump cavitation performance curve and distribution of cavitation bubbles. Next, based on the external characteristics experiment and high-speed photography experiment, the appropriate cavitation model for unsteady numerical calculation was selected. On the basis of vapor volume fraction distribution and the cavitation performance curve, four different typical points representing different cavitation coefficients were selected for further analyses. The direct boundary element method was used to calculate the variation characteristics of cavitation-induced noise at different cavitation coefficients. Finally, the peak-to-peak value of pressure fluctuation coefficient is defined as Д, and the pressure pulsating frequency domain signals were analyzed to further study the influence of pressure pulsation on acoustic field. The results show that the effect of pressure pulsation on noise is mainly focused on the discrete eigenvalues, and as for the broadband noise, the influence is not obvious. With the development of cavitation, axial passing frequency, 10- to 100-Hz frequency band, and 1000- to 3000-Hz frequency band show an increasing trend, while blade passing frequency and its harmonic frequencies show a decreasing trend. At the onset of cavitation, 1000- to 3000-Hz frequency band has the highest sensitivity for cavitation detection.

Kimmo Elo

During the last two decades single photographs and photograph corpora have gained in popularity as sources for historical research. In addition to their important function as carriers of the past, photographs also contain valuable information about past social relations. However, to utilise this information a researcher needs a more structured dataset, a photograph corpus containing rich metadata, which allows us to explore and analyse contextual information stored in alphanumeric form. My paper will exemplify how photography corpora could be used as a source for network analysis seeking to explore, reconstruct and visualise hidden historical social networks. The empirical case of my paper revolves around regional and interregional networks of East German dissident movement. The main empirical material explored for network analysis and visualisations consists of a large enriched photograph corpus on East German dissident movement maintained by Robert Havemann Foundation in Berlin. Based on this corpus my paper will explore the structure and dynamics of regional and interregional networks of East German opposition. The results introduce evidence that regional connectedness based on personal mobility among the East German dissidents both changes and increases over time, thus resulting in continuously evolving patterns of social interaction. Further, the analysis of Roland Jahn’s geospatial networks evidences the usefulness and power of historical network analysis when it comes to tackling changes in patterns of social interaction.

Biju Raju, N S D Raju, John Davis Akkara et al.

This article describes the method to make a do it yourself smartphone-based fundus camera which can image the central retina as well as the peripheral retina up to the pars plana. It is a cost-effective alternative to the fundus camera.

Renato Ambrósio Jr, Isaac Ramos, Allan Luz et al.

OBJECTIVE: To describe a novel technique for clinical characterization of corneal biomechanics using non-invasive dynamic imaging. METHODS: Corneal deformation response during non contact tonometry (NCT) is monitored by ultra-high-speed (UHS) photography. The Oculus Corvis ST (Scheimpflug Technology; Wetzlar, Germany) has a UHS Scheimpflug camera, taking over 4,300 frames per second and of a single 8mm horizontal slit, for monitoring corneal deformation response to NCT. The metered collimated air pulse or puff has a symmetrical configuration and fixed maximal internal pump pressure of 25 kPa. The bidirectional movement of the cornea in response to the air puff is monitored. RESULTS: Measurement time is 30ms, with 140 frames acquired. Advanced algorithms for edge detection of the front and back corneal contours are applied for every frame. IOP is calculated based on the first applanation moment. Deformation amplitude (DA) is determined as the highest displacement of the apex in the highest concavity (HC) moment. Applanation length (AL) and corneal velocity (CVel) are recorded during ingoing and outgoing phases. CONCLUSION: Corneal deformation can be monitored during non contact tonometry. The parameters generated provide clinical in vivo characterization of corneal biomechanical properties in two dimensions, which is relevant for different applications in Ophthalmology.