The Institute of Intelligent Robotics at Novosibirsk State University (NSU) has developed and launched a set of free online services based on iOk artificial intelligence for automatic analysis and identification of images taken using microscopes. The platform was designed to free scientists from performing routine tasks that arise when manually processing images. The press service of the Ministry of Education and Science of the Russian Federation reported this to socialbites.ca.
“Scientists are often faced with the task of characterizing images obtained from a microscope: for example, it is necessary to determine the average size or number of objects. “Previously, scientists had to perform these manipulations manually, spending a lot of effort and time,” Andrey Matveev, head of the laboratory for deep machine learning in physical methods at the NSU Institute of Intelligent Robotics, told socialbites.ca.
The iOk platform is a set of three online services based on artificial intelligence (AI) for image analysis. The services are called No Code ML, DLgram and ParticlesNN. The first is implemented as a bot in Telegram messaging programs, and the other is a web service. The basis of all programs is the Cascade Mask-RCNN neural network trained on 5 thousand objects.
All three programs are capable of working with a variety of images: images and video recordings from electron microscopes and digital cameras (including smartphones). They recognize various objects: nanoparticles, microorganisms, cells and more.
According to Matveev, NSU services differ from their counterparts in that they do not require high-resolution images. Additionally, the development in Russia can identify and ignore noise and light in images that are identified by other AI as separate objects, affecting the accuracy of reports.
“We have combined these into a single iOk platform for the convenience of users. Already the total number of its users is more than 500 experts,” added Andrey Matveev.
Previously AI helped Discover a new drug to treat anemia.