A novel similarity measure to evaluate image correspondence

Robert Marti; Reyer Zwiggelaar; Caroline M. E. Rubin

doi:10.1109/ICPR.2000.903511

A novel similarity measure to evaluate image correspondence

Robert Marti, Reyer Zwiggelaar, Caroline M. E. Rubin

Research output: Contribution to conference › Paper

Abstract

We have developed a novel similarity measure to evaluate image correspondence. Our method is based on the mutual information between images. The main difference to other mutual information approaches is that we incorporate spatial information using grey-level co-occurrence matrices, leading to a more general measurement. We have used this technique to evaluate two registration algorithms (local affine transformation and thin plate splines) applied to a dataset of mammographic images.

Original language	English
Number of pages	4
DOIs	https://doi.org/10.1109/ICPR.2000.903511
Publication status	Published - 03 Sept 2000
Externally published	Yes
Event	Proceedings 15th International Conference on Pattern Recognition: ICPR-2000 - Barcelona, Spain Duration: 03 Sept 2000 → 07 Sept 2000

Conference

Conference	Proceedings 15th International Conference on Pattern Recognition
Abbreviated title	ICPR-2000
Country/Territory	Spain
City	Barcelona
Period	03 Sept 2000 → 07 Sept 2000

Access to Document

10.1109/ICPR.2000.903511

Permanent link

Persistent link

Cite this

@conference{80e0edc750144d31a0ed9dc896328937,

title = "A novel similarity measure to evaluate image correspondence",

abstract = "We have developed a novel similarity measure to evaluate image correspondence. Our method is based on the mutual information between images. The main difference to other mutual information approaches is that we incorporate spatial information using grey-level co-occurrence matrices, leading to a more general measurement. We have used this technique to evaluate two registration algorithms (local affine transformation and thin plate splines) applied to a dataset of mammographic images.",

author = "Robert Marti and Reyer Zwiggelaar and Rubin, {Caroline M. E.}",

year = "2000",

month = sep,

day = "3",

doi = "10.1109/ICPR.2000.903511",

language = "English",

note = "Proceedings 15th International Conference on Pattern Recognition : ICPR-2000, ICPR-2000 ; Conference date: 03-09-2000 Through 07-09-2000",

}

TY - CONF

T1 - A novel similarity measure to evaluate image correspondence

AU - Marti, Robert

AU - Zwiggelaar, Reyer

AU - Rubin, Caroline M. E.

PY - 2000/9/3

Y1 - 2000/9/3

N2 - We have developed a novel similarity measure to evaluate image correspondence. Our method is based on the mutual information between images. The main difference to other mutual information approaches is that we incorporate spatial information using grey-level co-occurrence matrices, leading to a more general measurement. We have used this technique to evaluate two registration algorithms (local affine transformation and thin plate splines) applied to a dataset of mammographic images.

AB - We have developed a novel similarity measure to evaluate image correspondence. Our method is based on the mutual information between images. The main difference to other mutual information approaches is that we incorporate spatial information using grey-level co-occurrence matrices, leading to a more general measurement. We have used this technique to evaluate two registration algorithms (local affine transformation and thin plate splines) applied to a dataset of mammographic images.

U2 - 10.1109/ICPR.2000.903511

DO - 10.1109/ICPR.2000.903511

M3 - Paper

T2 - Proceedings 15th International Conference on Pattern Recognition

Y2 - 3 September 2000 through 7 September 2000

ER -

A novel similarity measure to evaluate image correspondence

Abstract

Conference

Access to Document

Permanent link

Fingerprint

Cite this