Endomicroscopic image retrieval and classification using invariant visual features

B. André, T. Vercauteren, A. Perchant, A. M. Buchner, M. B. Wallace, N. Ayache

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

18 Citations (Scopus)

Abstract

This paper investigates the use of modern content based image retrieval methods to classify endomicroscopic images into two categories: neoplastic (pathological) and benign. We describe first the method that maps an image into a visual feature signature which is a numerical vector invariant with respect to some particular classes of geometric and intensity transformations. Then we explain how these signatures are used to retrieve from a database the k closest images to a new image. The classification is finally achieved through a procedure of votes weighted by a proximity criterion (weighted k-nearest neighbors). Compared with several previously published alternatives whose maximal accuracy rate is almost 67% on the database, our approach yields an accuracy of 80% and offers promising perspectives.

Original languageEnglish (US)
Title of host publicationProceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009
Pages346-349
Number of pages4
DOIs
StatePublished - 2009
Event2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009 - Boston, MA, United States
Duration: Jun 28 2009Jul 1 2009

Other

Other2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009
CountryUnited States
CityBoston, MA
Period6/28/097/1/09

Fingerprint

Image classification
Image retrieval
Databases

Keywords

  • Bag of Visual Words (BVW) method
  • Content-based imageretrieval
  • Endomicroscopy
  • K-nearest neighbors classification

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

André, B., Vercauteren, T., Perchant, A., Buchner, A. M., Wallace, M. B., & Ayache, N. (2009). Endomicroscopic image retrieval and classification using invariant visual features. In Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009 (pp. 346-349). [5193055] https://doi.org/10.1109/ISBI.2009.5193055

Endomicroscopic image retrieval and classification using invariant visual features. / André, B.; Vercauteren, T.; Perchant, A.; Buchner, A. M.; Wallace, M. B.; Ayache, N.

Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009. 2009. p. 346-349 5193055.

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

André, B, Vercauteren, T, Perchant, A, Buchner, AM, Wallace, MB & Ayache, N 2009, Endomicroscopic image retrieval and classification using invariant visual features. in Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009., 5193055, pp. 346-349, 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009, Boston, MA, United States, 6/28/09. https://doi.org/10.1109/ISBI.2009.5193055
André B, Vercauteren T, Perchant A, Buchner AM, Wallace MB, Ayache N. Endomicroscopic image retrieval and classification using invariant visual features. In Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009. 2009. p. 346-349. 5193055 https://doi.org/10.1109/ISBI.2009.5193055
André, B. ; Vercauteren, T. ; Perchant, A. ; Buchner, A. M. ; Wallace, M. B. ; Ayache, N. / Endomicroscopic image retrieval and classification using invariant visual features. Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009. 2009. pp. 346-349
@inproceedings{fc03c5074592457685055827e11dcf57,
title = "Endomicroscopic image retrieval and classification using invariant visual features",
abstract = "This paper investigates the use of modern content based image retrieval methods to classify endomicroscopic images into two categories: neoplastic (pathological) and benign. We describe first the method that maps an image into a visual feature signature which is a numerical vector invariant with respect to some particular classes of geometric and intensity transformations. Then we explain how these signatures are used to retrieve from a database the k closest images to a new image. The classification is finally achieved through a procedure of votes weighted by a proximity criterion (weighted k-nearest neighbors). Compared with several previously published alternatives whose maximal accuracy rate is almost 67{\%} on the database, our approach yields an accuracy of 80{\%} and offers promising perspectives.",
keywords = "Bag of Visual Words (BVW) method, Content-based imageretrieval, Endomicroscopy, K-nearest neighbors classification",
author = "B. Andr{\'e} and T. Vercauteren and A. Perchant and Buchner, {A. M.} and Wallace, {M. B.} and N. Ayache",
year = "2009",
doi = "10.1109/ISBI.2009.5193055",
language = "English (US)",
isbn = "9781424439324",
pages = "346--349",
booktitle = "Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009",

}

TY - GEN

T1 - Endomicroscopic image retrieval and classification using invariant visual features

AU - André, B.

AU - Vercauteren, T.

AU - Perchant, A.

AU - Buchner, A. M.

AU - Wallace, M. B.

AU - Ayache, N.

PY - 2009

Y1 - 2009

N2 - This paper investigates the use of modern content based image retrieval methods to classify endomicroscopic images into two categories: neoplastic (pathological) and benign. We describe first the method that maps an image into a visual feature signature which is a numerical vector invariant with respect to some particular classes of geometric and intensity transformations. Then we explain how these signatures are used to retrieve from a database the k closest images to a new image. The classification is finally achieved through a procedure of votes weighted by a proximity criterion (weighted k-nearest neighbors). Compared with several previously published alternatives whose maximal accuracy rate is almost 67% on the database, our approach yields an accuracy of 80% and offers promising perspectives.

AB - This paper investigates the use of modern content based image retrieval methods to classify endomicroscopic images into two categories: neoplastic (pathological) and benign. We describe first the method that maps an image into a visual feature signature which is a numerical vector invariant with respect to some particular classes of geometric and intensity transformations. Then we explain how these signatures are used to retrieve from a database the k closest images to a new image. The classification is finally achieved through a procedure of votes weighted by a proximity criterion (weighted k-nearest neighbors). Compared with several previously published alternatives whose maximal accuracy rate is almost 67% on the database, our approach yields an accuracy of 80% and offers promising perspectives.

KW - Bag of Visual Words (BVW) method

KW - Content-based imageretrieval

KW - Endomicroscopy

KW - K-nearest neighbors classification

UR - http://www.scopus.com/inward/record.url?scp=70449418024&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70449418024&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2009.5193055

DO - 10.1109/ISBI.2009.5193055

M3 - Conference contribution

SN - 9781424439324

SP - 346

EP - 349

BT - Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009

ER -