A Genetic Algorithm for Projective Invariant Object Recognition

Peter W. M. Tsang; Albert T. S. Au

doi:10.1109/TENCON.1996.608705

A Genetic Algorithm for Projective Invariant Object Recognition

Peter W. M. Tsang
, Albert T. S. Au

Department of Electrical Engineering

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

13 Citations (Scopus)

Abstract

In this paper, a genetic algorithm is developed for recognition of near planar objects under projective transformation. The approach can be generalized in any 2D geometric transformation. No approximation to perspective projection is required, so the camera used for capturing the objects is allowed to locate at arbitrary position away from the scene. A genetic algorithm is employed to search for the optimal solution in order to identify the object and to estimate its location with reference to the model. Encouraged results were obtained by testing the approach from a number of industrial handtools.

Original language	English
Title of host publication	1996 IEEE TENCON - Digital Signal Processing Applications, Proceedings
Publisher	IEEE
Pages	58-61
Volume	1
ISBN (Print)	0780336798, 0780336801, 078033681X
DOIs	https://doi.org/10.1109/TENCON.1996.608705
Publication status	Published - Nov 1996
Event	1996 IEEE Region 10 Conference on Digital Signal Processing Applications (TENCON 96) - University of Western Australia, Perth, Australia Duration: 26 Nov 1996 → 29 Nov 1996

Conference

Conference	1996 IEEE Region 10 Conference on Digital Signal Processing Applications (TENCON 96)
Place	Australia
City	Perth
Period	26/11/96 → 29/11/96

Access Output

10.1109/TENCON.1996.608705

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{ce1a6a659d0c42fea6a58eaeadebb1e3,

title = "A Genetic Algorithm for Projective Invariant Object Recognition",

abstract = "In this paper, a genetic algorithm is developed for recognition of near planar objects under projective transformation. The approach can be generalized in any 2D geometric transformation. No approximation to perspective projection is required, so the camera used for capturing the objects is allowed to locate at arbitrary position away from the scene. A genetic algorithm is employed to search for the optimal solution in order to identify the object and to estimate its location with reference to the model. Encouraged results were obtained by testing the approach from a number of industrial handtools.",

author = "Tsang, \{Peter W. M.\} and Au, \{Albert T. S.\}",

year = "1996",

month = nov,

doi = "10.1109/TENCON.1996.608705",

language = "English",

isbn = "0780336798",

volume = "1",

pages = "58--61",

booktitle = "1996 IEEE TENCON - Digital Signal Processing Applications, Proceedings",

publisher = "IEEE",

address = "United States",

note = "1996 IEEE Region 10 Conference on Digital Signal Processing Applications (TENCON 96) ; Conference date: 26-11-1996 Through 29-11-1996",

}

TY - GEN

T1 - A Genetic Algorithm for Projective Invariant Object Recognition

AU - Tsang, Peter W. M.

AU - Au, Albert T. S.

PY - 1996/11

Y1 - 1996/11

N2 - In this paper, a genetic algorithm is developed for recognition of near planar objects under projective transformation. The approach can be generalized in any 2D geometric transformation. No approximation to perspective projection is required, so the camera used for capturing the objects is allowed to locate at arbitrary position away from the scene. A genetic algorithm is employed to search for the optimal solution in order to identify the object and to estimate its location with reference to the model. Encouraged results were obtained by testing the approach from a number of industrial handtools.

AB - In this paper, a genetic algorithm is developed for recognition of near planar objects under projective transformation. The approach can be generalized in any 2D geometric transformation. No approximation to perspective projection is required, so the camera used for capturing the objects is allowed to locate at arbitrary position away from the scene. A genetic algorithm is employed to search for the optimal solution in order to identify the object and to estimate its location with reference to the model. Encouraged results were obtained by testing the approach from a number of industrial handtools.

UR - https://www.scopus.com/pages/publications/0030312309

UR - https://www.scopus.com/pages/publications/0030312309#tab=impact

U2 - 10.1109/TENCON.1996.608705

DO - 10.1109/TENCON.1996.608705

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 0780336798

SN - 0780336801

SN - 078033681X

VL - 1

SP - 58

EP - 61

BT - 1996 IEEE TENCON - Digital Signal Processing Applications, Proceedings

PB - IEEE

T2 - 1996 IEEE Region 10 Conference on Digital Signal Processing Applications (TENCON 96)

Y2 - 26 November 1996 through 29 November 1996

ER -

A Genetic Algorithm for Projective Invariant Object Recognition

Abstract

Conference

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this