Transformational invariance — a primer
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 t...
Main Authors: | Forsyth, D, Mundy, JL, Zisserman, A |
---|---|
Format: | Journal article |
Language: | English |
Published: |
Elsevier
1992
|
Similar Items
-
Projectively invariant representations using implicit algebraic curves
by: Forsyth, D, et al.
Published: (1990) -
Efficient model library access by projectively invariant indexing functions
by: Rothwell, CA, et al.
Published: (2002) -
Using projective invariants for constant time library indexing in model based vision
by: Rothwell, CA, et al.
Published: (2012) -
Invariant descriptors for 3D object recognition and pose
by: Forsyth, D, et al.
Published: (1991) -
3D object recognition using invariance
by: Zisserman, A, et al.
Published: (1995)