Invariance--A new framework for vision

David Forsyth, Joseph L. Mundy, Andrew Zisserman, Christopher M. Brown

Research output: Chapter in Book/Report/Conference proceedingConference contribution


It is shown that curved planar objects have shape descriptors that are unaffected by the position, orientation and intrinsic parameters of the camera. These shape descriptors can be used to index quickly and efficiently into a large model base of curved planar objects, because their value is independent of pose and unaffected by perspective. Thus, recognition can proceed independent of calculating pose. Object curves are represented using conics, attached with a fitting technique that commutes with projection. This means that the pose of an object can be determined by backprojecting known conics. The authors show examples of recognition and pose determination using real image data.

Original languageEnglish (US)
Title of host publicationProc 3 Int Conf Comput Vision
PublisherPubl by IEEE
Number of pages8
ISBN (Print)0818620579
StatePublished - 1990
Externally publishedYes
EventProceedings 3rd International Conference on Computer Vision - Osaka, Jpn
Duration: Dec 4 1990Dec 7 1990

Publication series

NameProc 3 Int Conf Comput Vision


OtherProceedings 3rd International Conference on Computer Vision
CityOsaka, Jpn

ASJC Scopus subject areas

  • General Engineering


Dive into the research topics of 'Invariance--A new framework for vision'. Together they form a unique fingerprint.

Cite this