Evaluation of edge detectors using average risk

L.J. Spreeuwers; F. van der Heijden

doi:10.1109/ICPR.1992.202100

Evaluation of edge detectors using average risk

L.J. Spreeuwers
, F. van der Heijden

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

11 Citations (Scopus)

408 Downloads (Pure)

Abstract

A new method for evaluation of edge detectors, based on the average risk of a decision, is discussed. The average risk is a performance measure well-known in Bayesian decision theory. Since edge detection can be regarded as a compound decision making process, the performance of an edge detector is context dependent. Therefore, the application of average risk to edge detection is non-trivial. The paper describes a method to estimate the probabilities on a number of different types of (context dependent) errors. A weighted sum of these estimated probabilities represents the average risk. The weight coefficients define the cost function. The method is suitable, not only for the comparison of edge operators, but also for the determination of the weaknesses and strengths of a certain edge operator. This is demonstrated with some well-known edge operators

Original language	English
Title of host publication	Proceedings 11th IAPR International Conference on Pattern Recognition, 1992. Vol.III. Conference C: Image, Speech and Signal Analysis
Place of Publication	Piscataway, NJ
Publisher	IEEE
Pages	771-774
Number of pages	4
ISBN (Print)	0-8186-2920-7
DOIs	https://doi.org/10.1109/ICPR.1992.202100
Publication status	Published - 30 Aug 1992
Event	11th IAPR International Conference on Pattern Recognition, ICPR 1992 - The Hague, Netherlands Duration: 30 Aug 1992 → 3 Sept 1992 Conference number: 11

Conference

Conference	11th IAPR International Conference on Pattern Recognition, ICPR 1992
Abbreviated title	ICPR
Country/Territory	Netherlands
City	The Hague
Period	30/08/92 → 3/09/92

Access to Document

10.1109/ICPR.1992.202100

Spreeuwers92evaluationFinal published version, 315 KB

Evaluation of edge detectors using average risk
Spreeuwers, L. J. & van der Heijden, F., 1 Sept 1991, Enschede: University of Twente.
Research output: Book/Report › Report › Professional

Cite this

@inproceedings{04aefe61339a455186d4a1ee6a6a798d,

title = "Evaluation of edge detectors using average risk",

abstract = "A new method for evaluation of edge detectors, based on the average risk of a decision, is discussed. The average risk is a performance measure well-known in Bayesian decision theory. Since edge detection can be regarded as a compound decision making process, the performance of an edge detector is context dependent. Therefore, the application of average risk to edge detection is non-trivial. The paper describes a method to estimate the probabilities on a number of different types of (context dependent) errors. A weighted sum of these estimated probabilities represents the average risk. The weight coefficients define the cost function. The method is suitable, not only for the comparison of edge operators, but also for the determination of the weaknesses and strengths of a certain edge operator. This is demonstrated with some well-known edge operators",

author = "L.J. Spreeuwers and \{van der Heijden\}, F.",

year = "1992",

month = aug,

day = "30",

doi = "10.1109/ICPR.1992.202100",

language = "English",

isbn = "0-8186-2920-7",

pages = "771--774",

booktitle = "Proceedings 11th IAPR International Conference on Pattern Recognition, 1992. Vol.III. Conference C: Image, Speech and Signal Analysis",

publisher = "IEEE",

address = "United States",

note = "11th IAPR International Conference on Pattern Recognition, ICPR 1992, ICPR ; Conference date: 30-08-1992 Through 03-09-1992",

}

Spreeuwers, LJ & van der Heijden, F 1992, Evaluation of edge detectors using average risk. in Proceedings 11th IAPR International Conference on Pattern Recognition, 1992. Vol.III. Conference C: Image, Speech and Signal Analysis. IEEE, Piscataway, NJ, pp. 771-774, 11th IAPR International Conference on Pattern Recognition, ICPR 1992, The Hague, Netherlands, 30/08/92. https://doi.org/10.1109/ICPR.1992.202100

Evaluation of edge detectors using average risk. / Spreeuwers, L.J.; van der Heijden, F.
Proceedings 11th IAPR International Conference on Pattern Recognition, 1992. Vol.III. Conference C: Image, Speech and Signal Analysis. Piscataway, NJ: IEEE, 1992. p. 771-774.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Evaluation of edge detectors using average risk

AU - Spreeuwers, L.J.

AU - van der Heijden, F.

N1 - Conference code: 11

PY - 1992/8/30

Y1 - 1992/8/30

N2 - A new method for evaluation of edge detectors, based on the average risk of a decision, is discussed. The average risk is a performance measure well-known in Bayesian decision theory. Since edge detection can be regarded as a compound decision making process, the performance of an edge detector is context dependent. Therefore, the application of average risk to edge detection is non-trivial. The paper describes a method to estimate the probabilities on a number of different types of (context dependent) errors. A weighted sum of these estimated probabilities represents the average risk. The weight coefficients define the cost function. The method is suitable, not only for the comparison of edge operators, but also for the determination of the weaknesses and strengths of a certain edge operator. This is demonstrated with some well-known edge operators

AB - A new method for evaluation of edge detectors, based on the average risk of a decision, is discussed. The average risk is a performance measure well-known in Bayesian decision theory. Since edge detection can be regarded as a compound decision making process, the performance of an edge detector is context dependent. Therefore, the application of average risk to edge detection is non-trivial. The paper describes a method to estimate the probabilities on a number of different types of (context dependent) errors. A weighted sum of these estimated probabilities represents the average risk. The weight coefficients define the cost function. The method is suitable, not only for the comparison of edge operators, but also for the determination of the weaknesses and strengths of a certain edge operator. This is demonstrated with some well-known edge operators

U2 - 10.1109/ICPR.1992.202100

DO - 10.1109/ICPR.1992.202100

M3 - Conference contribution

SN - 0-8186-2920-7

SP - 771

EP - 774

BT - Proceedings 11th IAPR International Conference on Pattern Recognition, 1992. Vol.III. Conference C: Image, Speech and Signal Analysis

PB - IEEE

CY - Piscataway, NJ

T2 - 11th IAPR International Conference on Pattern Recognition, ICPR 1992

Y2 - 30 August 1992 through 3 September 1992

ER -

Evaluation of edge detectors using average risk

Abstract

Conference

Access to Document

Fingerprint

Research output

Evaluation of edge detectors using average risk

Cite this