English
Arabic
Chinese (Simplified)
Dutch
Esperanto
French
German
Greek
Italian
Japanese
Korean
Portuguese
Russian
Spanish
UrduA study is the first-of-its-kind to recognize American Sign Language (ASL) alphabet gestures using computer vision. Researchers developed a custom dataset of 29,820 static images of ASL hand gestures. Each image was annotated with 21 key landmarks on the hand, providing detailed spatial information about its structure and position. Combining MediaPipe and YOLOv8, a deep learning method they trained, with fine-tuning hyperparameters for the best accuracy, represents a groundbreaking and innovative approach that hasn’t been explored in previous research.
Tag: Computer Vision
The best AI strategy to recognize multiple objects in one image
Image classification is one of AI’s most common tasks, where a system is required to recognize an object from a given image. Yet real life requires us to recognize not a single standalone object but rather multiple objects appearing together in a given image.
This reality raises the question: what is the best strategy to tackle multi-object classification? The common approach is to detect each object individually and then classify them. But new research challenges this customary approach to multi-object classification tasks.
In an article published today in Physica A, researchers from Bar-Ilan University in Israel show how classifying objects together, through a process known as Multi-Label Classification (MLC), can surpass the common detection-based classification.
Automated machine learning robot unlocks new potential for genetics research
University of Minnesota Twin Cities researchers have constructed a robot that uses machine learning to fully automate a complicated microinjection process used in genetic research.
Computer Vision Is Superior to Surgeons in Identifying Spinal Implants
Computer vision model outperforms surgeons when identifying types of spinal implants.
New algorithms help four-legged robots run in the wild
A new system of algorithms developed by UC San Diego engineers enables four-legged robots to walk and run on challenging terrain while avoiding both static and moving obstacles. The work brings researchers a step closer to building robots that can perform search and rescue missions or collect information in places that are too dangerous or difficult for humans.
Making House Calls Guided by AI
Handheld computer vision and machine learning tool for identifying surgical wound infections debuts in rural Rwanda, enabling crucial care for women recovering from c-section in their homes. Project named first-prize winner in NIH Technology Accelerator Challenge for Maternal Health.
University of Minnesota student uses TikTok dance videos to solve problems in computer vision and machine learning
What if we used TikTok as a tool to further scientific research? University of Minnesota computer science Ph.D. student Yasamin Jafarian is doing just that, using data from the app to create more realistic 3D digital avatars.
Expert in Ecological Applications of AI Joins Newly Announced Imageomics Institute
Chuck Stewart, an expert in the ecological applications of computer vision, is part of the newly created Imageomics Institute, founded with a $15 million grant from the National Science Foundation to use images of living organisms to understand biological processes.
Rensselaer Expert in Ecological Applications of Computer Vision Joins NSF-Funded Artificial Research Institute
An expert in applying artificial intelligence (AI) to problems in animal ecology at Rensselaer Polytechnic Institute will join a team of researchers in a new $20 million National Science Foundation (NSF) Artificial Intelligence Research Institute announced on Thursday.
AI Learns to Predict Human Behavior from Videos
New Columbia Engineering study unveils a computer vision technique for giving machines a more intuitive sense for what will happen next by leveraging higher-level associations between people, animals, and objects.“Our algorithm is a step toward machines being able to make better predictions about human behavior, and thus better coordinate their actions with ours,” said Computer Science Professor Carl Vondrick. “Our results open a number of possibilities for human-robot collaboration, autonomous vehicles, and assistive technology.”
New smartphone app predicts vineyard yields earlier, more accurately
Cornell University engineers and plant scientists have teamed up to develop a low-cost system that allows grape growers to predict their yields much earlier in the season and more accurately than costly traditional methods.
Standard digital camera and AI to monitor soil moisture for affordable smart irrigation
Researchers at The University of South Australia have successfully tested a system that can monitor soil moisture using just a standard camera and an AI algorithm. The system holds huge potential as a simple, affordable solution for smart agriculture, allowing for automated, precision irrigation.
Tool transforms world landmark photos into 4D experiences
Using publicly available tourist photos of world landmarks such as the Trevi Fountain in Rome or Top of the Rock in New York City, Cornell University researchers have developed a method to create maneuverable 3D images that show changes in appearance over time.
AI software enables real-time 3D printing quality assessment
Oak Ridge National Laboratory researchers have developed artificial intelligence software for powder bed 3D printers that assesses the quality of parts in real time, without the need for expensive characterization equipment.
Research reflects how AI sees through the looking glass
Intrigued by how reflection changes images in subtle and not-so-subtle ways, a team of Cornell University researchers used artificial intelligence to investigate what sets originals apart from their reflections. Their algorithms learned to pick up on unexpected clues such as hair parts, gaze direction and, surprisingly, beards – findings with implications for training machine learning models and detecting faked images.