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...
主要な著者: | Forsyth, D, Mundy, JL, Zisserman, A |
---|---|
フォーマット: | Journal article |
言語: | English |
出版事項: |
Elsevier
1992
|
類似資料
-
Projectively invariant representations using implicit algebraic curves
著者:: Forsyth, D, 等
出版事項: (1990) -
Efficient model library access by projectively invariant indexing functions
著者:: Rothwell, CA, 等
出版事項: (2002) -
Using projective invariants for constant time library indexing in model based vision
著者:: Rothwell, CA, 等
出版事項: (2012) -
Invariant descriptors for 3D object recognition and pose
著者:: Forsyth, D, 等
出版事項: (1991) -
3D object recognition using invariance
著者:: Zisserman, A, 等
出版事項: (1995)