This book constitutes the strictly refereed post-workshop proceedings of the second International Workshop on Object Representation in Computer Vision, held in conjunction with ECCV '96 in Cambridge, UK, in April 1996.
The 15 revised full papers contained in the book were selected from 45 submissions for presentation at the workshop. Also included are three invited contributions based on the talks by Takeo Kanade, Jan Koenderink, and Ram Nevatia as well as a workshop report by the volume editors summarizing several panel discussions and the general state of the art in the area.
Author(s): Jean Ponce, Martial Hebert, Andrew Zisserman (auth.), Jean Ponce, Andrew Zisserman, Martial Hebert (eds.)
Series: Lecture Notes in Computer Science 1144
Edition: 1
Publisher: Springer-Verlag Berlin Heidelberg
Year: 1996
Language: English
Pages: 411
Tags: Pattern Recognition; Computer Graphics; Image Processing and Computer Vision; Artificial Intelligence (incl. Robotics); Systems and Information Theory in Engineering
Report on the 1996 international workshop on object representation in computer vision....Pages 1-8
From an intensity image to 3-D segmented descriptions....Pages 9-24
Recovering Generalized Cylinders by monocular vision....Pages 25-51
Combinatorial geometry for shape representation and indexing....Pages 53-78
Representing objects using topology....Pages 79-108
Curvature based signatures for object description and recognition....Pages 109-129
On 3D shape synthesis....Pages 131-148
Shape constancy in pictorial relief....Pages 149-164
Dimensionality of illumination manifolds in appearance matching....Pages 165-178
Learning object representations from lighting variations....Pages 179-199
Learning appearance models for object recognition....Pages 201-219
An image oriented CAD approach....Pages 221-245
An experimental comparison of appearance and geometric model based recognition....Pages 247-269
Virtualized reality: Being mobile in a visual scene....Pages 271-285
Generic shape learning and recognition....Pages 287-320
A hybrid approach to 3D representation....Pages 321-333
Finding pictures of objects in large collections of images....Pages 335-360
Beyond the Hough transform: Further properties of the R θ mapping and their applications....Pages 361-380
Non-Euclidean object representations for calibration-free video overlay....Pages 381-401
