Transformational invariance - a primer

David Forsyth, Joseph L. Mundy, Andrew Zisserman

Research output: Contribution to journalArticlepeer-review


The shape of objects seen in images depends on the viewpoint. This effect confounds recognition. We demonstrate a theoretical framework within which it is possible to construct descriptors for curves which do not vary with viewpoint. These descriptors are known as invariants. We use this framework to construct invariant shape descriptors for plane curves. These invariant shape descriptors make it possible to recognise plane curves, without explicitly determining the relationship between the curve reference frame and the camera coordinate system, and can be used to index quickly and efficiently into a large model base of curves. Many of these ideas are demonstrated by experiments on real image data.

Original languageEnglish (US)
Pages (from-to)39-45
Number of pages7
JournalImage and Vision Computing
Issue number1
StatePublished - 1992
Externally publishedYes


  • invariance
  • model-based vision
  • recognition
  • shape

ASJC Scopus subject areas

  • Signal Processing
  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Transformational invariance - a primer'. Together they form a unique fingerprint.

Cite this