What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Geometry
His primary areas of study are Artificial intelligence, Computer vision, Invariant, Image processing and Affine transformation.
His work on Image registration, Image moment and Image restoration as part of his general Artificial intelligence study is frequently connected to Viewpoints, thereby bridging the divide between different branches of science.
Jan Flusser integrates Image registration with Process in his research.
His study looks at the relationship between Invariant and fields such as Cognitive neuroscience of visual object recognition, as well as how they intersect with chemical problems.
As part of the same scientific family, Jan Flusser usually focuses on Image processing, concentrating on Feature vector and intersecting with Image segmentation, Subpixel rendering, Difference of Gaussians and Feature extraction.
His biological study spans a wide range of topics, including Character recognition, Convolution and Arithmetic.
His most cited work include:
- Image registration methods: a survey (5430 citations)
- Pattern recognition by affine moment invariants (671 citations)
- Moments and Moment Invariants in Pattern Recognition (393 citations)
What are the main themes of his work throughout his whole career to date?
Jan Flusser focuses on Artificial intelligence, Computer vision, Invariant, Affine transformation and Image registration.
His Artificial intelligence research is multidisciplinary, incorporating elements of Blind deconvolution and Pattern recognition.
His Computer vision study frequently links to related topics such as Convolution.
His work is dedicated to discovering how Invariant, Image moment are connected with Mathematical analysis and other disciplines.
His Affine transformation study combines topics from a wide range of disciplines, such as Discrete mathematics and Pattern recognition.
He integrates Image registration and Phase correlation in his studies.
He most often published in these fields:
- Artificial intelligence (57.92%)
- Computer vision (45.54%)
- Invariant (23.27%)
What were the highlights of his more recent work (between 2014-2021)?
- Artificial intelligence (57.92%)
- Computer vision (45.54%)
- Algorithm (12.38%)
In recent papers he was focusing on the following fields of study:
Jan Flusser mainly focuses on Artificial intelligence, Computer vision, Algorithm, Invariant and Mathematical analysis.
His Artificial intelligence study frequently draws connections to other fields, such as Pattern recognition.
His research integrates issues of Blind deconvolution and Robustness in his study of Computer vision.
The study incorporates disciplines such as Filter, Identification, Affine transformation, Representation and Noise reduction in addition to Algorithm.
His study in Invariant is interdisciplinary in nature, drawing from both Linear independence and Feature extraction.
His study on Hermite polynomials and Classical orthogonal polynomials is often connected to Velocity Moments as part of broader study in Mathematical analysis.
Between 2014 and 2021, his most popular works were:
- 2D and 3D Image Analysis by Moments (95 citations)
- Recognition of Images Degraded by Gaussian Blur (45 citations)
- Near infrared face recognition using Zernike moments and Hermite kernels (41 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Geometry
Jan Flusser mostly deals with Artificial intelligence, Mathematical analysis, Computer vision, Velocity Moments and Method of moments.
His study in the field of Image moment is also linked to topics like Phase correlation.
His Image moment research integrates issues from 3d image and Cognitive neuroscience of visual object recognition.
His work on Classical orthogonal polynomials, Jacobi polynomials and Chebyshev polynomials as part of general Mathematical analysis research is frequently linked to Hahn polynomials, bridging the gap between disciplines.
His Computer vision study combines topics in areas such as Blind deconvolution and Rotational symmetry.
His work focuses on many connections between Method of moments and other disciplines, such as Numerical stability, that overlap with his field of interest in Geometry, Polynomial basis, Image scaling and Scaling.
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.
