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...
المؤلفون الرئيسيون: | Forsyth, D, Mundy, JL, Zisserman, A |
---|---|
التنسيق: | Journal article |
اللغة: | English |
منشور في: |
Elsevier
1992
|
مواد مشابهة
-
Projectively invariant representations using implicit algebraic curves
حسب: Forsyth, D, وآخرون
منشور في: (1990) -
Efficient model library access by projectively invariant indexing functions
حسب: Rothwell, CA, وآخرون
منشور في: (2002) -
Using projective invariants for constant time library indexing in model based vision
حسب: Rothwell, CA, وآخرون
منشور في: (2012) -
Invariant descriptors for 3D object recognition and pose
حسب: Forsyth, D, وآخرون
منشور في: (1991) -
3D object recognition using invariance
حسب: Zisserman, A, وآخرون
منشور في: (1995)