What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Statistics
His primary areas of investigation include Artificial intelligence, Pattern recognition, Computer vision, Algorithm and RGB color model.
Artificial intelligence and Affine shape adaptation are frequently intertwined in his study.
His Pattern recognition research is multidisciplinary, incorporating elements of Histogram, Real image, Quantization and Image retrieval.
His Computer vision study frequently draws connections between related disciplines such as Tree.
His research in Algorithm intersects with topics in Discrete mathematics, Nonparametric statistics, Parametric statistics, Distance transform and Euclidean distance.
His studies in RGB color model integrate themes in fields like Segmentation, Tracking, Mean-shift, Scale-space segmentation and Time of flight.
His most cited work include:
- Gradient domain high dynamic range compression (1149 citations)
- Fast and robust Earth Mover's Distances (587 citations)
- Linear time Euclidean distance transform algorithms (407 citations)
What are the main themes of his work throughout his whole career to date?
Artificial intelligence, Computer vision, Algorithm, Pattern recognition and Pixel are his primary areas of study.
His work is connected to Image, Image processing, Epipolar geometry, Robustness and Feature, as a part of Artificial intelligence.
His work on Object, Motion estimation and Pose as part of general Computer vision study is frequently linked to Barcode, therefore connecting diverse disciplines of science.
Michael Werman has researched Algorithm in several fields, including Discrete mathematics, Probability distribution, Mathematical optimization and Bayesian probability.
As a part of the same scientific family, Michael Werman mostly works in the field of Pattern recognition, focusing on Histogram and, on occasion, Quantization.
His studies deal with areas such as Channel and Brightness as well as Pixel.
He most often published in these fields:
- Artificial intelligence (65.88%)
- Computer vision (47.06%)
- Algorithm (22.94%)
What were the highlights of his more recent work (between 2013-2021)?
- Artificial intelligence (65.88%)
- Computer vision (47.06%)
- Epipolar geometry (9.41%)
In recent papers he was focusing on the following fields of study:
Michael Werman mostly deals with Artificial intelligence, Computer vision, Epipolar geometry, Pixel and Algorithm.
His Artificial intelligence research is multidisciplinary, incorporating perspectives in Approximations of π and Convex function.
His Computer vision research includes themes of Motion and Similarity measure.
His biological study deals with issues like Silhouette, which deal with fields such as Background subtraction, Convex hull and Pattern recognition.
His Pixel study combines topics from a wide range of disciplines, such as Brightness, Illuminant D65, Color space, Optical flow and Robustness.
The study incorporates disciplines such as Ellipse, Enhanced Data Rates for GSM Evolution, Code, Square and Topology in addition to Algorithm.
Between 2013 and 2021, his most popular works were:
- Automatic recovery of the atmospheric light in hazy images (127 citations)
- Camera Calibration from Dynamic Silhouettes Using Motion Barcodes (21 citations)
- Efficient classification using the Euler characteristic (18 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Statistics
Michael Werman focuses on Artificial intelligence, Computer vision, Epipolar geometry, Pixel and Algorithm.
The study of Artificial intelligence is intertwined with the study of Radius in a number of ways.
His Computer vision research incorporates elements of Brightness, Similarity measure and Robustness.
His Pixel research incorporates themes from RGB color model and Principal component analysis.
His Algorithm study combines topics in areas such as Enhanced Data Rates for GSM Evolution, Code, Symmetry, Convolution and Wavelet.
His Object study integrates concerns from other disciplines, such as Image resolution, Computing Methodologies, Shape analysis and Depth map.
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.
