Articles tagged with Image Processing
A team of researchers has developed a MEMS scanning lidar that can detect objects reliably even in shaky environments. The long-range MEMS lidar prototype uses a digital controller to suppress errors caused by vibrations, allowing for stable 3D imaging and object detection.
Mayo Clinic researchers propose a novel computational model that links Alzheimer's disease symptoms to brain anatomy, revealing a complex relationship between mental processing and brain function. The model uses machine learning to analyze patient brain imaging data and compresses complex brain anatomy into a conceptual framework.
Researchers at Nara Institute of Science and Technology developed a new calibration method to compensate for variations in illumination while scanning stained-glass windows. This approach can help capture the colors of cultural artifacts in a lifelike way, even with long scanning times.
Researchers warn of machine learning bias when data published for one task is used to train algorithms for a different one. This can lead to compromised integrity and 'overly optimistic' results in medical imaging applications.
Australian researchers have mapped the visual systems of hoverflies to detect drones' acoustic signatures, showing a 30-49% improvement in detection rates compared to traditional methods. The technology has potential applications for aviation safety and combatting IED-carrying drones.
Researchers at Kaunas University of Technology improved an algorithm to detect Alzheimer's disease from MRI images, achieving over 98% accuracy. The new model uses a modified neural network and adapts to variations in data, such as differences in hospital equipment and patient positions.
The new device, Bio-FlatScope, uses a custom algorithm to reconstruct images of micron-scale targets like cells and blood vessels inside the body. The light captured by Bio-FlatScope can be refocused after the fact to reveal 3D details, making it potentially valuable for detecting cancer or sepsis.
Researchers at Bielefeld University have identified five key characteristics of mitosis in the microalga Volvox carteri, including a porous nuclear envelope and crucial centrosome function. They used confocal laser scanning microscopy to capture high-resolution images of live cell division and gain insights into the complex process.
Researchers are developing a new SWIR surgical microscope system to detect and remove cholesteatomas, a type of chronic otitis media. The microscope uses short-wave infrared light to illuminate blood, bacterial biofilms, cartilage, and soft tissue, making them distinguishable from each other.
A new fluorescent DNA label has been developed to visualize disrupted DNA architecture in cancer cells, with promising results for improved cancer diagnoses and risk stratification. The study showed that the label can distinguish normal tissue from precancerous and cancerous lesions.
Adversarially robust models capture aspects of human peripheral processing, with results showing similarity in image transformations and perception alignment. The study's findings shed light on the goals of peripheral processing in humans and could help improve machine learning models.
The KAUST team has created a flexible and efficient scintillation film using lead-free metal halides, detecting X-rays at levels 113 times lower than standard medical imaging doses. This breakthrough enhances medical, industrial and security X-ray imaging, offering significant improvements in spatial resolution.
Scientists observe atomic magnetic field and origin of magnetism in iron atoms using Magnetic-field-free Atomic-Resolution STEM (MARS) and Differential Phase Contrast (DPC) method. This breakthrough enables research and development of various magnetic materials and devices.
Developed by University of Seville researchers, the new methodology has a sensitivity of 100% and specificity of 87.5%. It can detect SARS-CoV-2 in saliva and synthetic viruses with minimal equipment and training.
A new dataset from NYU Tandon School of Engineering and Woven Planet Holdings promises to help visually impaired pedestrians and autonomous vehicles navigate complex urban settings. The robust dataset uses over 200,000 outdoor images to test visual place recognition technologies that can improve navigation accuracy.
A new microscope allows for real-time aberration-free dynamic speckle microscopy using compressed time-reversal matrix technology. This enables almost real-time volumetric adaptive optical imaging with reduced data acquisition time and improved lateral resolution.
Researchers found lower functional connectivity between brain areas involved in social and emotional processing in individuals at risk of developing alcohol use disorder. This impairment may affect their ability to interpret facial expressions and respond to their environment, increasing the likelihood of disordered drinking.
A new study found that children's face-perception abilities are impaired when wearing masks, with a 20% impairment rate compared to adults' 15%. This disruption can affect social interactions and relationships. Researchers highlight the need for future studies on the impact of mask-wearing on children's educational performance.
Researchers at the University of Groningen have developed an AI system that can recognize indoor spaces with high accuracy by combining image and audio data. The system achieved a 70% accuracy rate in recognizing nine different types of indoor spaces, surpassing previous results.
Researchers from KTU proposed a deep-learning-based method for 3D human shape reconstruction using limited-angle depth data. The method can be integrated with existing virtual reality tools and has potential applications in telemedicine and remote diagnostics.
A Bar-Ilan University study found that participants remembered large images 1.5 times more than small ones, regardless of detail or resolution. This phenomenon may affect screen quality and learning on smartphones, suggesting larger screens could be better for studying.
A team of researchers from the University of Groningen developed an AI-based system that can identify individual Holstein cows in a milking station based on their coat pattern. The system achieved a recognition rate of 99.7% and has several advantages, including non-invasiveness, cost-effectiveness, and scalability.
A new high-speed projector can project RGB images and invisible infrared images simultaneously and independently at a rate of almost 1,000 fps. This technology has vast potential for applications such as dynamic projection mapping, which requires real-time image control to match complex moving targets.
Researchers at Duke University developed a holographic system that can image and analyze tens of thousands of cells per minute to spot signs of disease. The technique distinguished between healthy samples and cancerous or pre-cancerous cells with nearly 100% accuracy, using just four basic cellular physical parameters.
The new system can produce high-quality images comparable to those of conventional cameras, with a compact design suitable for minimally invasive endoscopy and full-scene sensing. This breakthrough could revolutionize medical imaging and robotics with size and weight constraints.
A study has developed a method using dark-field microscopy and deep learning algorithms to identify microplastics in human cells, achieving an accuracy of 93% for 1-micron polystyrene particles. The technique has the potential to screen microplastics in various samples, reducing time-consuming data acquisition and processing steps.
A new study published in Frontiers in Psychology has identified specific facial features that can be used to distinguish children's faces from adult faces. These features include the shape of the nose and eyebrows for adult faces and the eye, jawline, and nasal bone for child faces.
A new virtual histology technology may reduce the need for invasive skin biopsies, providing a biopsy-free solution for rapid diagnosis of malignant skin tumors. The technology uses deep-learning frameworks to transform images of intact skin into detailed, virtually stained images.
A new imaging method measures individual photons, greatly reducing interference and improving spatial resolution by three times. The technology could also reduce radiation exposure during x-ray imaging, making it ideal for medical applications.
The Stanford Computational Imaging Lab has developed a technique to reduce speckling distortion in holographic displays, while another paper proposes a method to realistically represent the physics of 3D scenes. The new system uses neural networks and camera-in-the-loop calibration for real-time adjustments.
Researchers at Rice University are creating a 3D-printed smart helmet with embedded sensors to protect soldiers' brains against kinetic or directed-energy effects. The program aims to modernize standard-issue military helmets by incorporating advances in materials, image processing, artificial intelligence, and energy storage.
Researchers have demonstrated a new technique for cross-sectional medical images without the need for tomography, enabling faster and more accurate imaging. The breakthrough is made possible by ultrafast photon detectors that can precisely determine the arrival times of photons, allowing for reconstruction-free positron emission imaging.
Researchers have trained a neural network to detect anomalies in medical images, adapting it to the nature of medical imaging and achieving better results. The new method uses weakly supervised training and can spot small-scale anomalies, accelerating the work of histopathologists and radiologists.
A team of researchers has created a virtual fitting room system using AI and a bespoke robotic mannequin. The system can digitize garments in two hours and synthesize photorealistic images, allowing users to try on clothing in real-time.
Researchers at Hebrew University developed a novel approach to mapping brain white matter fiber architecture using Nissl staining. The technique, called Nissl-ST, reveals the hidden patterns and organization of glial cells in white matter, opening new avenues for studying brain development, aging, and neurodegenerative diseases.
Researchers at the University of Waterloo developed AI technology that can identify players by their jersey numbers in hockey videos with high accuracy. The system uses multi-task learning and a large dataset of over 54,000 images from NHL games to recognize sweater numbers.
The Imageomics Institute, led by The Ohio State University, aims to use machine learning methodologies to extract biological traits from images of living organisms. Experts like Chuck Stewart will utilize computer vision and artificial intelligence to help infer phylogenetic traits from images.
Researchers at Helmholtz-Zentrum Berlin have achieved a new world record in materials research by using X-ray microscopy to create 1000 three-dimensional images per second. This allows for the non-destructive study of fast processes in materials, enabling researchers to gain insights into material properties and behavior.
Researchers at the University of Rochester have developed a time-domain single-pixel imaging technique that detects ultrafast light pulses with high accuracy and speed. The new method can capture 5 femtojoule pulses with temporal sampling sizes as low as 16 femtoseconds, outperforming existing methods.
Scientists have developed a technique to enhance digital sensor capabilities beyond current limits, enabling applications in consumer photography, medical imaging, and space exploration. The new approach uses 'modulo' sampling to process a wider range of information, unlocking high dynamic range for sensors.
A team of researchers from the Beckman Institute for Advanced Science and Technology has developed a fast, accurate, and cost-effective COVID-19 test. Using label-free microscopic imaging combined with artificial intelligence, they can detect and classify SARS-CoV-2 in under one minute.
Scientists at Anglia Ruskin University have created a new way to experience Yellowstone's geysers through classical music. By sonifying the physical characteristics of the geothermal landscape, they've turned vibrations into melodies, harmonies, and rhythms. The result is an evolving musical representation of the earth, water, and steam.
A team of researchers at Osaka University created a custom dataset to train an AI algorithm to digitally remove unwanted objects from building façade images. The algorithm achieved high accuracy in inpainting occluded regions with digital inpainting.
A team of scientists has developed an efficient large-scale phase retrieval technique for realizing high-fidelity complex-domain phase imaging. The new method combines conventional optimization algorithms with deep learning techniques, achieving robustness to measurement noise and strong generalization. By comparing the reported method...
A study by Anglia Ruskin University found that weaker internal connections between the brain and organs are linked to negative body image. Adults with less efficient brains at detecting internal messages are more likely to experience body shame and weight preoccupation.
Researchers developed a method to overlay a virtual scale on acquired endoscope images in real-time, allowing accurate estimation of colorectal polyp sizes. The approach uses triangulation principles and minimal image processing, enabling cost-effective diagnosis without adding extra instrumentation.
Using complex-valued layers can improve performance against adversarial attacks without sacrificing efficiency. This technique, combined with gradient regularization, allows neural networks to resist small perturbations and maintain accuracy.
A team of scientists from Osaka University developed a machine learning method for classifying the type of building and its primary façade color using deep learning models applied to street-level images. This work may assist in fostering neighborhood cohesion and support urban renewal by providing tailored street-view datasets.
A team of researchers at Washington University in St. Louis has received a $3.12 million NIH grant to study neurovascular recovery after stroke. They aim to develop new neurovascular imaging technology using two-photon fluorescence microscopy and photoacoustic microscopy to visualize blood oxygen delivery in response to neuronal activity.
The team used machine learning technique generative adversarial networks to digitally remove clouds from aerial images, generating accurate datasets of building image masks. This work may help automate computer vision jobs critical to civil engineering, enabling the detection of buildings in areas without labeled training data.
Researchers have developed a dye-free method to visualize blood flow in the brain, allowing for detailed mapping of small capillaries and assessing blood flow rates. The technique has potential applications in understanding cardiovascular diseases, tumor growth, and targeted drug delivery.
Researchers at UCLA have developed a computational technique powered by artificial intelligence that transforms images of tissue previously stained with H&E into new ones with added special stains. The process takes less than one minute per tissue sample, significantly improving diagnoses in medical conditions such as organ transpl...
Scientists at Nara Institute of Science and Technology create a projected touchscreen system using just one camera and projector, eliminating the need for additional detectors. The system uses slope disparity gating to capture touch data with high efficiency, enabling portable projection systems for large interactive displays.
Scientists have developed a new live analysis system for plant stomata, allowing for rapid and affordable identification of desirable traits. This innovation has the potential to accelerate crop development for climate-resistance, addressing future food shortages.
A recent study published in Biosystems Engineering explores the potential of smartphone cameras to assess soil organic matter and evaluate soil fertility. The technique uses advanced image analysis and machine learning to predict SOM values rapidly and with high correlation to traditional soil analysis.
Researchers at Duke University developed a robotic imaging tool that can automatically detect and scan patients' eyes for eye diseases, producing clear images in under 50 seconds. The system uses optical coherence tomography and is designed to be safe and accessible for optometrist offices, primary-care clinics, and emergency departments.
A retrospective study of over 3,900 patients found that warming iohexol 350 contrast media did not significantly reduce adverse reactions or extravasations. The results suggest that maintaining the agent at room temperature is non-inferior to warming it to body temperature before injection.
A study published in Nature Communications reveals the visual system retains information from moving images, providing a consistent representation of surroundings. The researchers found that neuronal responses in deeper layers of the visual cortex exhibit 'perceptual constancy' and 'intrinsic persistence', ensuring stable encoding and ...
Researchers have developed a novel spectral-volumetric compressed ultrafast photography system that captures 5D information in a single snapshot. This breakthrough imaging technique enables new insights into ultrafast phenomena in physics and biochemistry.
A new imaging technique called DEEP enables researchers to image complex biological systems at high resolution and speeds previously impossible. This breakthrough may lead to new understandings of brain function and other biological processes.