What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Machine learning
The scientist’s investigation covers issues in Artificial intelligence, Computer vision, Pattern recognition, Cognitive neuroscience of visual object recognition and Image processing.
In general Computer vision study, his work on Feature, Motion estimation and Tracking often relates to the realm of Scale invariance, thereby connecting several areas of interest.
His studies deal with areas such as Object, Computation and 3D single-object recognition as well as Pattern recognition.
The various areas that David G. Lowe examines in his 3D single-object recognition study include Scale space and Scale-invariant feature transform.
The concepts of his Cognitive neuroscience of visual object recognition study are interwoven with issues in Feature extraction, Probabilistic logic and Missing data.
His Hough transform research includes themes of Machine learning, Point set registration and Maximally stable extremal regions.
His most cited work include:
- Distinctive Image Features from Scale-Invariant Keypoints (40185 citations)
- Object recognition from local scale-invariant features (11997 citations)
- FAST APPROXIMATE NEAREST NEIGHBORS WITH AUTOMATIC ALGORITHM CONFIGURATION (2109 citations)
What are the main themes of his work throughout his whole career to date?
David G. Lowe focuses on Artificial intelligence, Computer vision, Pattern recognition, Cognitive neuroscience of visual object recognition and Feature.
His Computer vision study incorporates themes from Robot and Mobile robot.
His Pattern recognition research is multidisciplinary, incorporating elements of Range and Object model.
David G. Lowe combines subjects such as Real image, Visual search, Search engine indexing and Feature vector with his study of Cognitive neuroscience of visual object recognition.
In his works, David G. Lowe conducts interdisciplinary research on 3D single-object recognition and Haar-like features.
As a part of the same scientific study, David G. Lowe usually deals with the Scale space, concentrating on Hough transform and frequently concerns with RANSAC.
He most often published in these fields:
- Artificial intelligence (83.93%)
- Computer vision (60.71%)
- Pattern recognition (34.82%)
What were the highlights of his more recent work (between 2008-2018)?
- Artificial intelligence (83.93%)
- Computer vision (60.71%)
- Pattern recognition (34.82%)
In recent papers he was focusing on the following fields of study:
Artificial intelligence, Computer vision, Pattern recognition, Cognitive neuroscience of visual object recognition and Object are his primary areas of study.
His work deals with themes such as Composite number and Support vector machine, which intersect with Computer vision.
His study looks at the intersection of Pattern recognition and topics like Naive bayes nearest neighbor with Machine learning.
The Cognitive neuroscience of visual object recognition study combines topics in areas such as Visualization, Histogram and Visual appearance.
His Feature research is multidisciplinary, incorporating perspectives in Salient and Tracking.
He studies Feature extraction, focusing on Scale-invariant feature transform in particular.
Between 2008 and 2018, his most popular works were:
- FAST APPROXIMATE NEAREST NEIGHBORS WITH AUTOMATIC ALGORITHM CONFIGURATION (2109 citations)
- Unsupervised Learning of Depth and Ego-Motion from Video (1074 citations)
- Perceptual Organization and Visual Recognition (1024 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Machine learning
David G. Lowe mostly deals with Artificial intelligence, Pattern recognition, Nearest neighbor search, Feature extraction and Linear search.
His study on Artificial intelligence is mostly dedicated to connecting different topics, such as Correctness.
He has researched Pattern recognition in several fields, including Artificial neural network and Embedding.
His Nearest neighbor graph and Large margin nearest neighbor study, which is part of a larger body of work in Nearest neighbor search, is frequently linked to Cover tree and Ball tree, bridging the gap between disciplines.
David G. Lowe interconnects Visualization, Cognitive neuroscience of visual object recognition, Hamming distance and Feature in the investigation of issues within Feature extraction.
His biological study spans a wide range of topics, including Theoretical computer science and Scale-invariant feature transform.
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.
