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...
Autors principals: | Forsyth, D, Mundy, JL, Zisserman, A |
---|---|
Format: | Journal article |
Idioma: | English |
Publicat: |
Elsevier
1992
|
Ítems similars
-
Projectively invariant representations using implicit algebraic curves
per: Forsyth, D, et al.
Publicat: (1990) -
Efficient model library access by projectively invariant indexing functions
per: Rothwell, CA, et al.
Publicat: (2002) -
Using projective invariants for constant time library indexing in model based vision
per: Rothwell, CA, et al.
Publicat: (2012) -
Invariant descriptors for 3D object recognition and pose
per: Forsyth, D, et al.
Publicat: (1991) -
3D object recognition using invariance
per: Zisserman, A, et al.
Publicat: (1995)