Proceedings ArticleDOI
A step toward generic object recognition
F. Tomita,M. Koizumi +1 more
- pp 632-636
Reads0
Chats0
TLDR
The authors propose an approach to define objects qualitatively and hierarchically by generic shapes (primitives) arranged by generic relations so that a class of objects has the same description and to recognize them in a parallel and bottom-up way in the image.Abstract:
The authors propose an approach to define objects qualitatively and hierarchically by generic shapes (primitives) arranged by generic relations so that a class of objects has the same description and to recognize them in a parallel and bottom-up way in the image. >read more
Citations
More filters
Proceedings ArticleDOI
R&D of versatile 3D vision system VVV
Fumiaki Tomita,Takashi Yoshimi,Toshio Ueshiba,Yoshihiro Kawai,Yasushi Sumi,T. Matsushita,N. Ichimura,K. Sugimoto,Yutaka Ishiyama +8 more
TL;DR: An advanced 3D vision system VVV (Versatile Volumetric Vision) which can be used for many purposes in many fields; robotics, medical and welfare, CAD, VR, etc.
Proceedings ArticleDOI
Boundary segmentation by detection of corner, inflection and transition points
K. Sugimoto,F. Tomita +1 more
TL;DR: A new method for the second step of object recognition, boundary segmentation, which can detect not only corners but inflection points on which the sign of the curvature changes and transitional points onWhich a line and a curve connect smoothly without any delicate threshold is presented.
Proceedings ArticleDOI
Detection of skewed-symmetrical shape
K. Sugimoto,F. Tomita +1 more
TL;DR: The proposed method can detect the accurate skewed symmetrical axes of not only polygonal patterns but also curved patterns in a complex image even if some parts of the patterns are occluded.
References
More filters
Journal ArticleDOI
Book review: PERCEPTUAL ORGANIZATION AND VISUAL RECOGNITION by David G. Lowe (Kluwer Academic Publishers)
TL;DR: The book summarizes research conducted by David Lowe, over a six year period, first as a graduate student at Stanford University and later on the SCERPO vision system at the Courant Institute of Mathematics at New York University.
Proceedings ArticleDOI
Qualitative and quantitative matching of solid models and images of 3D objects
M. Koizumi,F. Tomita +1 more
TL;DR: A model-based vision system which recognizes 3D objects in an image is presented, and a candidate transformation is quantitatively hypothesized for each object by initially matching a few corresponding points in the primitive.