Sciweavers

725 search results - page 63 / 145
» Invariances in kernel methods: From samples to objects
Sort
View
ICRA
2008
IEEE
204views Robotics» more  ICRA 2008»
14 years 3 months ago
Active exploration and keypoint clustering for object recognition
— Object recognition is a challenging problem for artificial systems. This is especially true for objects that are placed in cluttered and uncontrolled environments. To challenge...
Gert Kootstra, Jelmer Ypma, Bart de Boer
CVPR
2007
IEEE
14 years 11 months ago
Virtual Recovery of the Deteriorated Art Object based on AR Technology
In this paper, the virtual restoration method of the art piece in the real world is proposed. The correction pattern for restoration is generated from non damaged object's im...
Toshiyuki Amano, Ryo Suzuki
CVPR
2010
IEEE
14 years 5 months ago
Safety in Numbers: Learning Categories from Few Examples with Multi Model Knowledge Transfer
Learning object categories from small samples is a challenging problem, where machine learning tools can in general provide very few guarantees. Exploiting prior knowledge may be ...
Tatiana Tommasi, Francesco Orabona, Barbara Caputo
COMPGEOM
2007
ACM
14 years 29 days ago
Medial axis approximation from inner Voronoi balls: a demo of the Mesecina tool
We illustrate a simple algorithm for approximating the medial axis of a 2D shape with smooth boundary from a sample of this boundary. The algorithm is compared to a more general a...
Balint Miklos, Joachim Giesen, Mark Pauly
ICCV
2009
IEEE
1821views Computer Vision» more  ICCV 2009»
15 years 1 months ago
Feature Correspondence and Deformable Object Matching via Agglomerative Correspondence Clustering
We present an efficient method for feature correspondence and object-based image matching, which exploits both photometric similarity and pairwise geometric consistency from local ...
Minsu Cho (Seoul National University), Jungmin Lee...