Abstract
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 language | English (US) |
|---|---|
| Pages (from-to) | 39-45 |
| Number of pages | 7 |
| Journal | Image and Vision Computing |
| Volume | 10 |
| Issue number | 1 |
| DOIs | |
| State | Published - Jan 1 1992 |
| Externally published | Yes |
Fingerprint
Keywords
- invariance
- model-based vision
- recognition
- shape
ASJC Scopus subject areas
- Signal Processing
- Computer Vision and Pattern Recognition
Cite this
Transformational invariance - a primer. / Forsyth, David; Mundy, Joseph L.; Zisserman, Andrew.
In: Image and Vision Computing, Vol. 10, No. 1, 01.01.1992, p. 39-45.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Transformational invariance - a primer
AU - Forsyth, David
AU - Mundy, Joseph L.
AU - Zisserman, Andrew
PY - 1992/1/1
Y1 - 1992/1/1
N2 - 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.
AB - 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.
KW - invariance
KW - model-based vision
KW - recognition
KW - shape
UR - http://www.scopus.com/inward/record.url?scp=0026679132&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0026679132&partnerID=8YFLogxK
U2 - 10.1016/0262-8856(92)90082-E
DO - 10.1016/0262-8856(92)90082-E
M3 - Article
AN - SCOPUS:0026679132
VL - 10
SP - 39
EP - 45
JO - Image and Vision Computing
JF - Image and Vision Computing
SN - 0262-8856
IS - 1
ER -