A continuous probabilistic framework for image matching

Hayit Greenspan; Jacob Goldberger; Lenny Ridel

doi:10.1006/cviu.2001.0946

A continuous probabilistic framework for image matching

Hayit Greenspan^*, Jacob Goldberger, Lenny Ridel

^*Corresponding author for this work

Department of Bio-Medical Engineering

Research output: Contribution to journal › Article › peer-review

Abstract

In this paper we describe a probabilistic image matching scheme in which the image representation is continuous and the similarity measure and distance computation are also defined in the continuous domain. Each image is first represented as a Gaussian mixture distribution and images are compared and matched via a probabilistic measure of similarity between distributions. A common probabilistic and continuous framework is applied to the representation as well as the matching process, ensuring an overall system that is theoretically appealing. Matching results are investigated and the application to an image retrieval system is demonstrated.

Original language	English
Pages (from-to)	384-406
Number of pages	23
Journal	Computer Vision and Image Understanding
Volume	84
Issue number	3
DOIs	https://doi.org/10.1006/cviu.2001.0946
State	Published - Dec 2001

Keywords

Gaussian mixture modeling
Image matching
Image representation
Kullback-Leibler distance
Probabilistic matching

Access to Document

10.1006/cviu.2001.0946

Cite this

@article{be214a8a257b4ad39c0edacc6efb7a77,

title = "A continuous probabilistic framework for image matching",

abstract = "In this paper we describe a probabilistic image matching scheme in which the image representation is continuous and the similarity measure and distance computation are also defined in the continuous domain. Each image is first represented as a Gaussian mixture distribution and images are compared and matched via a probabilistic measure of similarity between distributions. A common probabilistic and continuous framework is applied to the representation as well as the matching process, ensuring an overall system that is theoretically appealing. Matching results are investigated and the application to an image retrieval system is demonstrated.",

keywords = "Gaussian mixture modeling, Image matching, Image representation, Kullback-Leibler distance, Probabilistic matching",

author = "Hayit Greenspan and Jacob Goldberger and Lenny Ridel",

note = "Funding Information: Hayit Greenspan was supported by the Eshkol Grant of the Ministry of Science. Part of the work was supported by the Israeli Ministry of Science, Grant 05530462.",

year = "2001",

month = dec,

doi = "10.1006/cviu.2001.0946",

language = "אנגלית",

volume = "84",

pages = "384--406",

journal = "Computer Vision and Image Understanding",

issn = "1077-3142",

publisher = "Academic Press Inc.",

number = "3",

}

TY - JOUR

T1 - A continuous probabilistic framework for image matching

AU - Greenspan, Hayit

AU - Goldberger, Jacob

AU - Ridel, Lenny

N1 - Funding Information: Hayit Greenspan was supported by the Eshkol Grant of the Ministry of Science. Part of the work was supported by the Israeli Ministry of Science, Grant 05530462.

PY - 2001/12

Y1 - 2001/12

N2 - In this paper we describe a probabilistic image matching scheme in which the image representation is continuous and the similarity measure and distance computation are also defined in the continuous domain. Each image is first represented as a Gaussian mixture distribution and images are compared and matched via a probabilistic measure of similarity between distributions. A common probabilistic and continuous framework is applied to the representation as well as the matching process, ensuring an overall system that is theoretically appealing. Matching results are investigated and the application to an image retrieval system is demonstrated.

AB - In this paper we describe a probabilistic image matching scheme in which the image representation is continuous and the similarity measure and distance computation are also defined in the continuous domain. Each image is first represented as a Gaussian mixture distribution and images are compared and matched via a probabilistic measure of similarity between distributions. A common probabilistic and continuous framework is applied to the representation as well as the matching process, ensuring an overall system that is theoretically appealing. Matching results are investigated and the application to an image retrieval system is demonstrated.

KW - Gaussian mixture modeling

KW - Image matching

KW - Image representation

KW - Kullback-Leibler distance

KW - Probabilistic matching

UR - http://www.scopus.com/inward/record.url?scp=0035556168&partnerID=8YFLogxK

U2 - 10.1006/cviu.2001.0946

DO - 10.1006/cviu.2001.0946

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

AN - SCOPUS:0035556168

SN - 1077-3142

VL - 84

SP - 384

EP - 406

JO - Computer Vision and Image Understanding

JF - Computer Vision and Image Understanding

IS - 3

ER -

A continuous probabilistic framework for image matching

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this