Image classification based on focus

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

1 Citation (Scopus)

Abstract

The performance of most image classification algorithms deteriorates in the presence of out-of-focus blur. Thus, it is essential to either correct the focus of the input images or leave them out of the training set. There exist many focus metrics for auto-focusing, but they generally give a relative focus value. Our technique combines some of the best performing focus metrics to obtain a new focus measure using which we can separate in-focus images from out-of-focus ones. We also compare our technique with the existing ones and show that it performs better. The classifier was tested on a dataset of ovarian images obtained using confocal microendoscopy.

Original languageEnglish (US)
Title of host publicationProceedings - International Conference on Image Processing, ICIP
Pages397-400
Number of pages4
DOIs
StatePublished - 2008
Event2008 IEEE International Conference on Image Processing, ICIP 2008 - San Diego, CA, United States
Duration: Oct 12 2008Oct 15 2008

Other

Other2008 IEEE International Conference on Image Processing, ICIP 2008
CountryUnited States
CitySan Diego, CA
Period10/12/0810/15/08

Fingerprint

Image classification
Classifiers

Keywords

  • Focus detection
  • Image classification

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Patel, M. B., Rodriguez, J. J., & Gmitro, A. F. (2008). Image classification based on focus. In Proceedings - International Conference on Image Processing, ICIP (pp. 397-400). [4711775] https://doi.org/10.1109/ICIP.2008.4711775

Image classification based on focus. / Patel, Mehul B.; Rodriguez, Jeffrey J; Gmitro, Arthur F.

Proceedings - International Conference on Image Processing, ICIP. 2008. p. 397-400 4711775.

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

Patel, MB, Rodriguez, JJ & Gmitro, AF 2008, Image classification based on focus. in Proceedings - International Conference on Image Processing, ICIP., 4711775, pp. 397-400, 2008 IEEE International Conference on Image Processing, ICIP 2008, San Diego, CA, United States, 10/12/08. https://doi.org/10.1109/ICIP.2008.4711775
Patel MB, Rodriguez JJ, Gmitro AF. Image classification based on focus. In Proceedings - International Conference on Image Processing, ICIP. 2008. p. 397-400. 4711775 https://doi.org/10.1109/ICIP.2008.4711775
Patel, Mehul B. ; Rodriguez, Jeffrey J ; Gmitro, Arthur F. / Image classification based on focus. Proceedings - International Conference on Image Processing, ICIP. 2008. pp. 397-400
@inproceedings{fba3640e45a04736b7d713810dce63b5,
title = "Image classification based on focus",
abstract = "The performance of most image classification algorithms deteriorates in the presence of out-of-focus blur. Thus, it is essential to either correct the focus of the input images or leave them out of the training set. There exist many focus metrics for auto-focusing, but they generally give a relative focus value. Our technique combines some of the best performing focus metrics to obtain a new focus measure using which we can separate in-focus images from out-of-focus ones. We also compare our technique with the existing ones and show that it performs better. The classifier was tested on a dataset of ovarian images obtained using confocal microendoscopy.",
keywords = "Focus detection, Image classification",
author = "Patel, {Mehul B.} and Rodriguez, {Jeffrey J} and Gmitro, {Arthur F}",
year = "2008",
doi = "10.1109/ICIP.2008.4711775",
language = "English (US)",
isbn = "1424417643",
pages = "397--400",
booktitle = "Proceedings - International Conference on Image Processing, ICIP",

}

TY - GEN

T1 - Image classification based on focus

AU - Patel, Mehul B.

AU - Rodriguez, Jeffrey J

AU - Gmitro, Arthur F

PY - 2008

Y1 - 2008

N2 - The performance of most image classification algorithms deteriorates in the presence of out-of-focus blur. Thus, it is essential to either correct the focus of the input images or leave them out of the training set. There exist many focus metrics for auto-focusing, but they generally give a relative focus value. Our technique combines some of the best performing focus metrics to obtain a new focus measure using which we can separate in-focus images from out-of-focus ones. We also compare our technique with the existing ones and show that it performs better. The classifier was tested on a dataset of ovarian images obtained using confocal microendoscopy.

AB - The performance of most image classification algorithms deteriorates in the presence of out-of-focus blur. Thus, it is essential to either correct the focus of the input images or leave them out of the training set. There exist many focus metrics for auto-focusing, but they generally give a relative focus value. Our technique combines some of the best performing focus metrics to obtain a new focus measure using which we can separate in-focus images from out-of-focus ones. We also compare our technique with the existing ones and show that it performs better. The classifier was tested on a dataset of ovarian images obtained using confocal microendoscopy.

KW - Focus detection

KW - Image classification

UR - http://www.scopus.com/inward/record.url?scp=69949167694&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=69949167694&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2008.4711775

DO - 10.1109/ICIP.2008.4711775

M3 - Conference contribution

AN - SCOPUS:69949167694

SN - 1424417643

SN - 9781424417643

SP - 397

EP - 400

BT - Proceedings - International Conference on Image Processing, ICIP

ER -