Improving edge detection by an objective edge evaluation

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

Edge detection is conventionally performed in an open-loop system. No feedback from the outcome of the detection operation is provided. The quality of the resulting edge image, thus, tends to be uncontrollable. The performance of edge detection can be improved by conducting the operation in a closed-loop system. This system performs an on-line objective edge evaluation. The evaluation process computes a set of edge metrics for the resulting image. An overall edge strength measurement of the image is obtained. No a priori knowledge about the edge distributions in the image is required for the measurement. Feedback of the evaluation adjusts, or guides the adjustment of, the edge operator parameters, thus improving the quality of the resulting edge images.

Original languageEnglish (US)
Title of host publicationApplied Computing
Subtitle of host publicationTechnological Challenges of the 1990's
PublisherPubl by ACM
Pages459-468
Number of pages10
ISBN (Print)089791502X
StatePublished - Dec 1 1992
EventProceedings of the 1992 ACM/SIGAPP Symposium on Applied Computing - SAC '92 - Kansas City, KS, USA
Duration: Mar 1 1992Mar 3 1992

Publication series

NameApplied Computing: Technological Challenges of the 1990's

Other

OtherProceedings of the 1992 ACM/SIGAPP Symposium on Applied Computing - SAC '92
CityKansas City, KS, USA
Period3/1/923/3/92

Fingerprint

Edge detection
Feedback
Closed loop systems

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Zhu, Q. (1992). Improving edge detection by an objective edge evaluation. In Applied Computing: Technological Challenges of the 1990's (pp. 459-468). (Applied Computing: Technological Challenges of the 1990's). Publ by ACM.

Improving edge detection by an objective edge evaluation. / Zhu, Qiuming.

Applied Computing: Technological Challenges of the 1990's. Publ by ACM, 1992. p. 459-468 (Applied Computing: Technological Challenges of the 1990's).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zhu, Q 1992, Improving edge detection by an objective edge evaluation. in Applied Computing: Technological Challenges of the 1990's. Applied Computing: Technological Challenges of the 1990's, Publ by ACM, pp. 459-468, Proceedings of the 1992 ACM/SIGAPP Symposium on Applied Computing - SAC '92, Kansas City, KS, USA, 3/1/92.
Zhu Q. Improving edge detection by an objective edge evaluation. In Applied Computing: Technological Challenges of the 1990's. Publ by ACM. 1992. p. 459-468. (Applied Computing: Technological Challenges of the 1990's).
Zhu, Qiuming. / Improving edge detection by an objective edge evaluation. Applied Computing: Technological Challenges of the 1990's. Publ by ACM, 1992. pp. 459-468 (Applied Computing: Technological Challenges of the 1990's).
@inproceedings{390ceb587204454f905bcb4e9ae710cb,
title = "Improving edge detection by an objective edge evaluation",
abstract = "Edge detection is conventionally performed in an open-loop system. No feedback from the outcome of the detection operation is provided. The quality of the resulting edge image, thus, tends to be uncontrollable. The performance of edge detection can be improved by conducting the operation in a closed-loop system. This system performs an on-line objective edge evaluation. The evaluation process computes a set of edge metrics for the resulting image. An overall edge strength measurement of the image is obtained. No a priori knowledge about the edge distributions in the image is required for the measurement. Feedback of the evaluation adjusts, or guides the adjustment of, the edge operator parameters, thus improving the quality of the resulting edge images.",
author = "Qiuming Zhu",
year = "1992",
month = "12",
day = "1",
language = "English (US)",
isbn = "089791502X",
series = "Applied Computing: Technological Challenges of the 1990's",
publisher = "Publ by ACM",
pages = "459--468",
booktitle = "Applied Computing",

}

TY - GEN

T1 - Improving edge detection by an objective edge evaluation

AU - Zhu, Qiuming

PY - 1992/12/1

Y1 - 1992/12/1

N2 - Edge detection is conventionally performed in an open-loop system. No feedback from the outcome of the detection operation is provided. The quality of the resulting edge image, thus, tends to be uncontrollable. The performance of edge detection can be improved by conducting the operation in a closed-loop system. This system performs an on-line objective edge evaluation. The evaluation process computes a set of edge metrics for the resulting image. An overall edge strength measurement of the image is obtained. No a priori knowledge about the edge distributions in the image is required for the measurement. Feedback of the evaluation adjusts, or guides the adjustment of, the edge operator parameters, thus improving the quality of the resulting edge images.

AB - Edge detection is conventionally performed in an open-loop system. No feedback from the outcome of the detection operation is provided. The quality of the resulting edge image, thus, tends to be uncontrollable. The performance of edge detection can be improved by conducting the operation in a closed-loop system. This system performs an on-line objective edge evaluation. The evaluation process computes a set of edge metrics for the resulting image. An overall edge strength measurement of the image is obtained. No a priori knowledge about the edge distributions in the image is required for the measurement. Feedback of the evaluation adjusts, or guides the adjustment of, the edge operator parameters, thus improving the quality of the resulting edge images.

UR - http://www.scopus.com/inward/record.url?scp=0026960659&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026960659&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0026960659

SN - 089791502X

T3 - Applied Computing: Technological Challenges of the 1990's

SP - 459

EP - 468

BT - Applied Computing

PB - Publ by ACM

ER -