Contribution to Science
Employees of the Institute of Artificial Intelligence not only help enterprises get economic benefits from the AI implementation, but also continue to actively develop scientific directions in the AI and its applications. The key scientific papers are below.
Computer vision based on diffractive nanophotonics and deep learning:
L. Doskolovich et al., Design of diffractive lenses operating at several wavelengths, Optics Express, 2020

A. Nikonorov et al., Deep learning-based imaging using single-lens and multi-aperture diffractive optical systems, IEEE ICCV workshop Learning for Computational imaging, 2019

A. Nikonorov et al., Toward ultralightweight remote sensing with harmonic lenses and convolutional neural networks, IEEE JSTARS, 2018

A. Nikonorov et al., Image restoration in diffractive optical systems using deep learning and deconvolution, Computer Optics, 2017

A. Nikonorov et al., Fresnel lens imaging with post-capture image processing, IEEE CVPR workshop Computational Cameras and Displays, 2015
Cognitive research, open source machine learning-based platform of neurofeedback, OpenNFT.org:
Bryukhovetskiy A.S. et al., Human mind has microwave electromagnetic nature and can be recorded and processed, Progress in Brain Research, 2020

Koush Y. et al., OpenNFT: An open-source Python/Matlab framework for real-time fMRI neurofeedback training based on activity; connectivity and multivariate pattern analysis, Neuroimage, 2017

Koush Y. et al., Real-time fMRI data for testing OpenNFT functionality, Data in brief, 2017
Color and hyperspectral image processing:
Kazanskiy N., et al., An airborne offner imaging hyperspectrometer with radially-fastened primary elements, Sensors, 2020

Nikonorov A. et al., Correcting color and hyperspectral images with identification of distortion model, Pattern recognition letters, 2016
Artificial intelligence in medicine:
N. Smelkina et al., Reconstruction of anatomical structures using statistical shape modeling, Computer Optics, 2017

A. Nikonorov et al., Vessel segmentation for noisy CT data with quality measure based on single-point contrast-to-noise ratio, International Conference on E-Business and Telecommunications, 2015