Planar object recognition using projective shape representation

C. A. Rothwell, A. Zisserman, David Alexander Forsyth, J. L. Mundy

Research output: Contribution to journalArticle

Abstract

We describe a model based recognition system, called LEWIS, for the identification of planar objects based on a projectively invariant representation of shape. The advantages of this shape description include simple model acquisition (direct from images), no need for camera calibration or object pose computation, and the use of index functions. We describe the feature construction and recognition algorithms in detail and provide an analysis of the combinatorial advantages of using index functions. Index functions are used to select models from a model base and are constructed from projective invariants based on algebraic curves and a canonical projective coordinate frame. Examples are given of object recognition from images of real scenes, with extensive object libraries. Successful recognition is demonstrated despite partial occlusion by unmodelled objects, and realistic lighting conditions.

Original languageEnglish (US)
Pages (from-to)57-99
Number of pages43
JournalInternational Journal of Computer Vision
Volume16
Issue number1
DOIs
StatePublished - Sep 1 1995
Externally publishedYes

Fingerprint

Object recognition
Lighting
Cameras
Calibration

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Planar object recognition using projective shape representation. / Rothwell, C. A.; Zisserman, A.; Forsyth, David Alexander; Mundy, J. L.

In: International Journal of Computer Vision, Vol. 16, No. 1, 01.09.1995, p. 57-99.

Research output: Contribution to journalArticle

Rothwell, C. A. ; Zisserman, A. ; Forsyth, David Alexander ; Mundy, J. L. / Planar object recognition using projective shape representation. In: International Journal of Computer Vision. 1995 ; Vol. 16, No. 1. pp. 57-99.
@article{e2337d92bccb4f818614ffe3839fb99e,
title = "Planar object recognition using projective shape representation",
abstract = "We describe a model based recognition system, called LEWIS, for the identification of planar objects based on a projectively invariant representation of shape. The advantages of this shape description include simple model acquisition (direct from images), no need for camera calibration or object pose computation, and the use of index functions. We describe the feature construction and recognition algorithms in detail and provide an analysis of the combinatorial advantages of using index functions. Index functions are used to select models from a model base and are constructed from projective invariants based on algebraic curves and a canonical projective coordinate frame. Examples are given of object recognition from images of real scenes, with extensive object libraries. Successful recognition is demonstrated despite partial occlusion by unmodelled objects, and realistic lighting conditions.",
author = "Rothwell, {C. A.} and A. Zisserman and Forsyth, {David Alexander} and Mundy, {J. L.}",
year = "1995",
month = "9",
day = "1",
doi = "10.1007/BF01428193",
language = "English (US)",
volume = "16",
pages = "57--99",
journal = "International Journal of Computer Vision",
issn = "0920-5691",
publisher = "Springer Netherlands",
number = "1",

}

TY - JOUR

T1 - Planar object recognition using projective shape representation

AU - Rothwell, C. A.

AU - Zisserman, A.

AU - Forsyth, David Alexander

AU - Mundy, J. L.

PY - 1995/9/1

Y1 - 1995/9/1

N2 - We describe a model based recognition system, called LEWIS, for the identification of planar objects based on a projectively invariant representation of shape. The advantages of this shape description include simple model acquisition (direct from images), no need for camera calibration or object pose computation, and the use of index functions. We describe the feature construction and recognition algorithms in detail and provide an analysis of the combinatorial advantages of using index functions. Index functions are used to select models from a model base and are constructed from projective invariants based on algebraic curves and a canonical projective coordinate frame. Examples are given of object recognition from images of real scenes, with extensive object libraries. Successful recognition is demonstrated despite partial occlusion by unmodelled objects, and realistic lighting conditions.

AB - We describe a model based recognition system, called LEWIS, for the identification of planar objects based on a projectively invariant representation of shape. The advantages of this shape description include simple model acquisition (direct from images), no need for camera calibration or object pose computation, and the use of index functions. We describe the feature construction and recognition algorithms in detail and provide an analysis of the combinatorial advantages of using index functions. Index functions are used to select models from a model base and are constructed from projective invariants based on algebraic curves and a canonical projective coordinate frame. Examples are given of object recognition from images of real scenes, with extensive object libraries. Successful recognition is demonstrated despite partial occlusion by unmodelled objects, and realistic lighting conditions.

UR - http://www.scopus.com/inward/record.url?scp=0029378123&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029378123&partnerID=8YFLogxK

U2 - 10.1007/BF01428193

DO - 10.1007/BF01428193

M3 - Article

AN - SCOPUS:0029378123

VL - 16

SP - 57

EP - 99

JO - International Journal of Computer Vision

JF - International Journal of Computer Vision

SN - 0920-5691

IS - 1

ER -