Computer Vision News - October 2020

2 Artificial Intelligence 44 Computer Vision News has found great new stories, written somewhere else by somebody else. We share them with you, adding a short comment. Enjoy! A I S P O T L I G H T N E W S The Subtle Effects of Blood Circulation Can Be Used to Detect Deep Fakes This is only one of the many articles discussing two recent works by two researchers at Binghamton University ( Umur Aybars Ciftci and Lijun Yin ) and one at Intel ( Ilke Demir ). Yes, THAT ILKE! The principle is that the software they created takes advantage of the fact that real videos of people contain physiological signals that are not visible to the eye. In particular, video of a person’s face contains subtle shifts in color that result from pulses in blood circulation. Have a look at the article: it will tell you about the FakeCatcher and about inconsistencies in photoplethysmography , or PPG . It also gives you the link to the studies. Read More ML model detects arthritis early Thanks to machine learning, early indications of serious conditions can be spotted with enough confidence to recommend further testing. In this work published on PNAS, Researchers at the University of Pittsburgh School of Medicine and Carnegie Mellon University College of Engineering have created a machine-learning algorithm that can detect subtle signs of osteoarthritis, often missed by trained radiologists, on an MRI scan taken years before symptoms even begin. Knowing which patients will develop arthritis will help make more effective testing of potential remedies. More AI in Orthopedics here . Read More A bird’s-eye view of deep learning in bioimage analysis UNSW scientist Erik Meijering (a long-time friend of our magazine) has prepared a sort of review of reviews about Deep Learning , from the perspective of his own field of research: biomedical imaging and bioimage analysis in particular. Deep learning technologies are fundamentally transforming how we acquire, process, analyze and interpret data, with potentially far- reaching consequences for healthcare. Erik gives the big picture, with 300+ references to papers providing more details. He hopes this would be especially helpful if you're new to the field. More Deep Learning works here . Read More