Transformational invariance - a primer

David Forsyth; Joseph L. Mundy; Andrew Zisserman

doi:10.1016/0262-8856(92)90082-E

Transformational invariance - a primer

David Forsyth, Joseph L. Mundy, Andrew Zisserman

Research output: Contribution to journal › Article › peer-review

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	https://doi.org/10.1016/0262-8856(92)90082-E
State	Published - 1992
Externally published	Yes

Keywords

invariance
model-based vision
recognition
shape

ASJC Scopus subject areas

Signal Processing
Computer Vision and Pattern Recognition

Access to Document

10.1016/0262-8856(92)90082-E

Fingerprint Dive into the research topics of 'Transformational invariance - a primer'. Together they form a unique fingerprint.

Cite this

@article{5d79ffde23e74ce8af9b2852fdffffee,

title = "Transformational invariance - a primer",

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.",

keywords = "invariance, model-based vision, recognition, shape",

author = "David Forsyth and Mundy, {Joseph L.} and Andrew Zisserman",

note = "Funding Information: David Forsyth acknowledges the support of Magda-len College, Oxford. Joseph L Mundy acknowledges the support of the General Electric Coolidge Fellowship. Andrew Zisserman acknowledges the support of the Science and Engineering Research Council.",

year = "1992",

doi = "10.1016/0262-8856(92)90082-E",

language = "English (US)",

volume = "10",

pages = "39--45",

journal = "Image and Vision Computing",

issn = "0262-8856",

publisher = "Elsevier Limited",

number = "1",

}

TY - JOUR

T1 - Transformational invariance - a primer

AU - Forsyth, David

AU - Mundy, Joseph L.

AU - Zisserman, Andrew

N1 - Funding Information: David Forsyth acknowledges the support of Magda-len College, Oxford. Joseph L Mundy acknowledges the support of the General Electric Coolidge Fellowship. Andrew Zisserman acknowledges the support of the Science and Engineering Research Council.

PY - 1992

Y1 - 1992

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 -

Transformational invariance - a primer

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Cite this