Explore the vast range of titles available.

All-optical image processing based on metasurfaces is a swiftly advancing field of technology, due to its high speed, large integrability and inherently low energy requirements. So far, the proposed devices have been focusing on canonical operations, such as differentiations to perform edge detection across all objects in a complex scene. Yet, undesired background noise and clutter can hinder such operations, requiring target selection with digital post-processing which inherently limits the overall accuracy, efficiency and speed. Here, we introduce an optical solution for real-time size-selective image processing and experimentally demonstrate the concept with a metal-dielectric-metal film performing a spatial band-pass filter in momentum space. We show high-resolution (~0.9 μm) edge detection and real-time dynamic denoising, ideally suited for bio-imaging applications and target recognitions. Our demonstrated k -space filtering metasurface expands the scope of nonlocal flat optics for analog image processing, ushering in opportunities for ultra-compact, cost-effective, and multifunctional image processors. All-optical image processing using metasurfaces is advancing due to its high speed, integrability, and low energy consumption, yet background noise and clutter hinder the progress. In this work, a real-time optical image processor is introduced, using a metal-dielectric-metal film to perform spatial band-pass filtering in momentum space enabling high-resolution edge detection and real-time dynamic denoising.

In this paper we will search in analysis the matrices (SVD) and (GSVD) in terms of the relationship between their matrices after touching and briefly about the idea of each. Where we will two analyze matrices A(m, p) and B(n, p) using the techniques above and we compare between each of the two analyzes 'for the purpose of reaching a final relationship connecting between the matrices of the two analyze. This relationship can be utilized it in image processors, encryption and image enhancement as well as text and video. Perhaps in a later research we will focus on determining the relationships between the matrices of other analyzes such as (QR) and (LU) analysis.

Strongly scattering conditions are detrimental to imaging. Conventional methods rely solely on post-processing techniques to enhance the ballistic components of an obscured target to recover the image; however, they struggle in complex conditions where the ballistic components are heavily overwhelmed by scattering. In this work, we present an optical meta-image-processor (MIP) that tailors the scattered point spread function of the imaging system to enable high-quality, deep imaging through strongly scattering media. The MIP performs both Laplacian and Gaussian operations in a single device, effectively suppressing background interference and Gaussian noise in the obscured image. Experimental results demonstrate that clear information can be recognized with the MIP, even when the optical thickness of the scattering medium reaches a challenging value of 17.05. Without the MIP, such imaging depth cannot be achieved through direct imaging, even when combined with any other post-processing techniques. Additionally, the MIP shows potential for enhancing the diagnostic performance of fundus cameras in the presence of cataracts. Both simulated and experimental evidence confirms the MIP’s capability to reveal hidden information under strongly scattering conditions, underscoring its promising potential to enhance imaging depth in biomedical imaging, machine vision, and artificial intelligence, especially in complex environments. This work presents a meta-image-processor enabling optical image processing system to achieve improved penetration depth through strongly scattering media, advancing imaging technology for visualization through deeper and more complex media.

Artificial intelligence (AI) has transformed art and design education, giving students new ways to create, explore, and learn. Unfortunately, there is fear among academicians that students will use AI, especially text-to-image generators like Midjourney or Dall-E, as an illegal shortcut in creating their work. This article examines how generative AI solutions, such as text-to-image generators, can help students create innovative and sustainable designs while promoting academic integrity. The article shows how AI in art and design education can equip students with the skills and knowledge to succeed in a rapidly changing digital landscape. This research uses a qualitative method by analyzing the apps and literature reviews in journals and documents related to the problems studied. Case studies show how AI-based solutions can help students create innovative and sustainable designs while promoting academic integrity. Integrating controlled AI- based approaches in art and design education can promote academic integrity, creativity, and sustainability. AI-based art and design education solutions may help society become more innovative and sustainable. This article concludes that art and design educators must embrace AI-based solutions to prepare students for a rapidly changing digital world.

Bubble plumes play an important role in both natural and engineered aquatic systems. Optical imaging has been widely used to study bubble size distributions, meandering, and plume growth. Machine learning (ML) offers new opportunities in analyzing optical images of bubble plumes. However, its application is limited by the lack of large, labeled image data sets that realistically represent plume conditions. Here, we introduce PlumeDEBuG, a synthetic image generator designed to reproduce key physical characteristics of bubble plumes, including bubble size distributions and spatial organization, using images derived from laboratory experiments. We first constructed an experimental database of more than 86,000 isolated bubbles of 1–15 mm with associated geometric labels. PlumeDEBuG enables users to generate synthetic plume images by specifying bubble size distributions (uniform, Gaussian, log‐normal, bimodal, or Weibull) and arranging bubbles with either Gaussian or random spatial patterns to resemble void fraction profiles. Validation against laboratory plume images confirms that the generated data sets replicate plume statistics. Finally, we trained deep learning (DL) models (YOLOv8 and SAM) on PlumeDEBuG images and show improved detection accuracy from their pretrained models. Across the images used in this study, the result showed a mean precision of 0.99 in IoU = 0.5 (mAP@50) and 0.91 averaged over IoU thresholds from 0.50 to 0.95 (mAP@50–95) using YOLOv8, and along with an average instance detection rate of 82.6% based on SAM segmentation. Based on our evaluation, we found that the apparent void fraction has a strong influence on the performance of DL models in detecting bubbles.

Researchers gave successive versions of a large language model information produced by previous generations of the AI — and observed rapid collapse. Researchers gave successive versions of a large language model information produced by previous generations of the AI — and observed rapid collapse. Credit: M. Boháček & H. Farid /ArXiv (CC BY 4.0) Example images generated after iterative retraining increasing from 25% (top row) to 100% (bottom row) of SD-generated faces.

Generative AI has gained a lot of attention in society, business, and science. This trend has increased since 2018, and the big breakthrough came in 2022. In particular, AI-based text and image generators are now widely used. This raises a variety of ethical issues. The present paper first gives an introduction to generative AI and then to applied ethics in this context. Three specific image generators are presented: DALL-E 2, Stable Diffusion, and Midjourney. The author goes into technical details and basic principles, and compares their similarities and differences. This is followed by an ethical discussion. The paper addresses not only risks, but opportunities for generative AI. A summary with an outlook rounds off the article.

Pharmaceutical drug dosage forms are critical for ensuring the effective and safe delivery of active pharmaceutical ingredients to patients. However, traditional formulation development often relies on extensive lab and animal experimentation, which can be time-consuming and costly. This manuscript presents a generative artificial intelligence method that creates digital versions of drug products from images of exemplar products. This approach employs an image generator guided by critical quality attributes, such as particle size and drug loading, to create realistic digital product variations that can be analyzed and optimized digitally. This paper shows how this method was validated through two case studies: one for the determination of the amount of material that will create a percolating network in an oral tablet product and another for the optimization of drug distribution in a long-acting HIV inhibitor implant. The results demonstrate that the generative AI method accurately predicts a percolation threshold of 4.2% weight of microcrystalline cellulose and generates implant formulations with controlled drug loading and particle size distributions. Comparisons with real samples reveal that the synthesized structures exhibit comparable particle size distributions and transport properties in release media. Pharmaceutical drug dosage forms are traditionally determined through extensive physical experimentation. Here, the authors present a generative AI method that creates digital drug products from images, matching and improving critical quality attributes such as particle size and drug loading.

We report on the experimental realization of a quasi-one-dimensional photonic graphene ribbon supporting four flat-bands (FBs). We study the dynamics of fundamental and dipolar modes, which are analogous to the s and p orbitals, respectively. In the experiment, both modes (orbitals) are effectively decoupled from each other, implying two sets of six bands, where two of them are completely flat (dispersionless). Using an image generator setup, we excite the s and p FB modes and demonstrate their non-diffracting propagation for the first time. Our results open an exciting route towards photonic emulation of higher orbital dynamics.

Pose-guided image and video synthesis is very challenging due to large variation and occlusion. Failing to disentangle the shape and the style of clothing, previous methods cannot fully control the image generation process, which limits their applications on person image/video editing. In this paper, we design a novel decoupled generator for person image and video synthesis, which is able to generate realistic images with desired poses, textures and semantic layouts. We adopt a two-stage framework with a parsing generator and an image generator to tackle this ill-posed problem. We first synthesize a human semantic parsing aligned with the target pose and then transfer the image information to generate the target image. To decouple the shape and the style of clothing, we propose joint global and local per-region encoding and normalization to predict the reasonable style of clothing for invisible regions. We also propose spatial-aware normalization to retain the spatial details in the source image. In order to capture large deformations for person video synthesis, we propose a region-based flow module with positional encoding to predict the dense correspondences between the source image and the target image, while disentangling the shape and the style of clothing. Experimental results show the superior performance of our model on pose-guided image/video synthesis. Besides, the results of texture transfer and parsing editing show that our model can be applied to person image and video editing. Code, dataset and models are available at: https://github.com/Zhangjinso/PISE.