What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Statistics
The scientist’s investigation covers issues in Artificial intelligence, Computer vision, Pattern recognition, Facial recognition system and Image processing.
Artificial intelligence is represented through his Pixel, Face detection, Feature extraction, Facial expression and Face research.
His work deals with themes such as Stereopsis, Segmentation and Interpolation, which intersect with Pixel.
His Computer vision research includes elements of Computer graphics and Pattern recognition.
His work focuses on many connections between Pattern recognition and other disciplines, such as Object, that overlap with his field of interest in Viola–Jones object detection framework.
Takeo Kanade has included themes like Matching, Algorithm, Line and Invariant in his Image processing study.
His most cited work include:
- An iterative image registration technique with an application to stereo vision (10317 citations)
- Neural network-based face detection (3348 citations)
- Shape and motion from image streams under orthography: a factorization method (2516 citations)
What are the main themes of his work throughout his whole career to date?
Takeo Kanade mainly investigates Artificial intelligence, Computer vision, Pattern recognition, Image processing and Computer graphics.
His Artificial intelligence study focuses mostly on Pixel, Robotics, Image, Object and Motion estimation.
His study ties his expertise on Robustness together with the subject of Computer vision.
Takeo Kanade works mostly in the field of Pattern recognition, limiting it down to topics relating to Facial recognition system and, in certain cases, Facial expression.
His study connects Pattern recognition and Image processing.
His research on Computer graphics frequently links to adjacent areas such as Virtual reality.
He most often published in these fields:
- Artificial intelligence (70.42%)
- Computer vision (57.95%)
- Pattern recognition (11.86%)
What were the highlights of his more recent work (between 2008-2020)?
- Artificial intelligence (70.42%)
- Computer vision (57.95%)
- Pattern recognition (11.86%)
In recent papers he was focusing on the following fields of study:
Takeo Kanade mainly focuses on Artificial intelligence, Computer vision, Pattern recognition, Image segmentation and Feature extraction.
Image, Image processing, Segmentation, Pixel and Feature are among the areas of Artificial intelligence where the researcher is concentrating his efforts.
His studies in Computer vision integrate themes in fields like Robot, Robustness and Microscopy.
He has researched Pattern recognition in several fields, including Contextual image classification, Supervised learning and Cluster analysis.
His Image segmentation research focuses on Image restoration and how it connects with Image formation.
His work carried out in the field of Feature extraction brings together such families of science as Video tracking and Feature detection.
Between 2008 and 2020, his most popular works were:
- The Extended Cohn-Kanade Dataset (CK+): A complete dataset for action unit and emotion-specified expression (2042 citations)
- Convolutional Pose Machines (1304 citations)
- Multi-PIE (1124 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Statistics
Takeo Kanade spends much of his time researching Artificial intelligence, Computer vision, Pattern recognition, Feature extraction and Image segmentation.
His research in Feature, Pose, Active appearance model, Image processing and Segmentation are components of Artificial intelligence.
His Computer vision study integrates concerns from other disciplines, such as Software and Robustness.
The various areas that Takeo Kanade examines in his Pattern recognition study include Object, Initialization and Solid modeling.
His research integrates issues of Feature detection, Stem cell, Visualization, Hidden Markov model and Search algorithm in his study of Feature extraction.
The study incorporates disciplines such as Anisotropic diffusion, Maximization, Pixel, Approximation algorithm and Thresholding in addition to Image segmentation.
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.
