H
Hiroshi Murase
Researcher at Nagoya University
Publications - 517
Citations - 8489
Hiroshi Murase is an academic researcher from Nagoya University. The author has contributed to research in topics: Feature (computer vision) & Partial discharge. The author has an hindex of 33, co-authored 502 publications receiving 8038 citations. Previous affiliations of Hiroshi Murase include Nippon Telegraph and Telephone & Columbia University.
Papers
More filters
Journal ArticleDOI
Visual learning and recognition of 3-D objects from appearance
Hiroshi Murase,Shree K. Nayar +1 more
TL;DR: A near real-time recognition system with 20 complex objects in the database has been developed and a compact representation of object appearance is proposed that is parametrized by pose and illumination.
Journal ArticleDOI
Moving object recognition in eigenspace representation: gait analysis and lip reading
Hiroshi Murase,Rie Sakai +1 more
TL;DR: A new method to calculate the spatio-temporal correlation efficiently in a parametric eigenspace representation for moving object recognition that reduces the computational cost of correlation-based comparison between image sequences.
Proceedings ArticleDOI
Learning and recognition of 3D objects from appearance
Hiroshi Murase,Shree K. Nayar +1 more
TL;DR: The authors address the problem of automatically learning object models for recognition and pose estimation as one of matching visual appearance rather than shape and present a new compact representation of object appearance that is parameterized by pose and illumination.
Journal ArticleDOI
Subspace methods for robot vision
TL;DR: The proposed appearance representation has several applications in robot vision, including a precise visual positioning system, a real-time visual tracking system, and areal-time temporal inspection system.
Proceedings ArticleDOI
Real-time 100 object recognition system
TL;DR: A real-time vision system is described that can recognize 100 complex three-dimensional objects and its recognition rate was found to be 100% and object pose was estimated with a mean absolute error of 2.02 degrees and standard deviation of 1.67 degrees.