What is he best known for?
The fields of study he is best known for:
- Statistics
- Artificial intelligence
- Computer vision
The scientist’s investigation covers issues in Artificial intelligence, Algorithm, Computer vision, Image processing and Image restoration.
Vladimir Katkovnik combines subjects such as Filter and Pattern recognition with his study of Artificial intelligence.
Vladimir Katkovnik works on Pattern recognition which deals in particular with Sparse approximation.
His biological study spans a wide range of topics, including Mean squared error, Mathematical optimization, Noise and Time–frequency analysis.
Vladimir Katkovnik studies Computer vision, focusing on Similarity in particular.
His Image processing research incorporates elements of Wiener filter, Decorrelation and Discrete cosine transform.
His most cited work include:
- Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering (5161 citations)
- NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results (555 citations)
- Pointwise Shape-Adaptive DCT for High-Quality Denoising and Deblocking of Grayscale and Color Images (532 citations)
What are the main themes of his work throughout his whole career to date?
Vladimir Katkovnik mostly deals with Algorithm, Artificial intelligence, Computer vision, Phase and Pattern recognition.
His work carried out in the field of Algorithm brings together such families of science as Beamforming, Mathematical optimization and Signal processing.
His Artificial intelligence study deals with Filter intersecting with Smoothing.
Vladimir Katkovnik regularly links together related areas like Noise in his Computer vision studies.
His Phase research integrates issues from Amplitude, Wavefront and Optics.
His Pattern recognition research is multidisciplinary, relying on both Non-local means, Image, Image denoising, Noise and Gaussian noise.
He most often published in these fields:
- Algorithm (39.17%)
- Artificial intelligence (37.08%)
- Computer vision (20.83%)
What were the highlights of his more recent work (between 2017-2021)?
- Optics (17.50%)
- Phase (18.75%)
- Hyperspectral imaging (7.50%)
In recent papers he was focusing on the following fields of study:
Vladimir Katkovnik focuses on Optics, Phase, Hyperspectral imaging, Wavefront and Phase retrieval.
His Phase study integrates concerns from other disciplines, such as Amplitude, Filter, Iterative reconstruction and Image formation.
Hyperspectral imaging is a primary field of his research addressed under Artificial intelligence.
His research in the fields of Training set overlaps with other disciplines such as Collaborative filtering.
His research in Noise reduction intersects with topics in Object, Singular value decomposition, Signal processing and Pattern recognition.
His work on Sparse approximation is typically connected to Domain as part of general Pattern recognition study, connecting several disciplines of science.
Between 2017 and 2021, his most popular works were:
- Single Image Super-Resolution Based on Wiener Filter in Similarity Domain. (41 citations)
- Nonlocality-Reinforced Convolutional Neural Networks for Image Denoising (41 citations)
- Surface relief and refractive index gratings patterned in chalcogenide glasses and studied by off-axis digital holography. (14 citations)
In his most recent research, the most cited papers focused on:
- Statistics
- Artificial intelligence
- Optics
Vladimir Katkovnik mainly focuses on Optics, Artificial intelligence, Algorithm, Pattern recognition and Holography.
Artificial intelligence and Matrix decomposition are two areas of study in which Vladimir Katkovnik engages in interdisciplinary research.
His Algorithm research includes themes of Wavelength, Multiplexing, Terahertz spectroscopy and technology and Absolute phase.
His work in the fields of Neural coding overlaps with other areas such as Gaussian.
His study explores the link between Holography and topics such as Time domain that cross with problems in Image quality, Phase imaging, Signal processing and Quality.
In his research, Domain, Sparse approximation and Singular value decomposition is intimately related to Hyperspectral imaging, which falls under the overarching field of Noise reduction.
This overview was generated by a machine learning system which analysed the scientist’s
body of work. If you have any feedback, you can
contact us
here.
