Detecting paper fibre cross sections in microtomy images

Peter Kontschieder, Michael Donoser, Horst Bischof, Johannes Kritzinger, Wolfgang Bauer

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Abstract

The goal of this work is the fully-automated detection of cellulose fibre cross sections in microtomy images. A lack of significant appearance information makes edges the only reliable cue for detection. We present a novel and highly discriminative edge fragment descriptor that represents angular relations between fragment points. We train a Random Forest with a plurality of these descriptors including their respective center votes. In such a way, the Random Forest exploits the knowledge about the object centroid for detection using a generalized Hough voting scheme. In the experiments we found that our method is able to robustly detect fibre cross sections in microtomy images and can therefore serve as initialization for successive fibre segmentation or tracking algorithms.

Original languageEnglish
Title of host publicationProceedings for ICPR 2010
Publisher.
Pages316-319
Number of pages4
ISBN (Print)9780769541099
DOIs
Publication statusPublished - 2010
Event20th International Conference on Pattern Recognition (ICPR) - Istanbul, Turkey
Duration: 23 Aug 201026 Aug 2010

Conference

Conference20th International Conference on Pattern Recognition (ICPR)
CountryTurkey
CityIstanbul
Period23/08/1026/08/10

Fingerprint

Fibers
Cellulose
Experiments

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Kontschieder, P., Donoser, M., Bischof, H., Kritzinger, J., & Bauer, W. (2010). Detecting paper fibre cross sections in microtomy images. In Proceedings for ICPR 2010 (pp. 316-319). [5597795] .. https://doi.org/10.1109/ICPR.2010.86

Detecting paper fibre cross sections in microtomy images. / Kontschieder, Peter; Donoser, Michael; Bischof, Horst; Kritzinger, Johannes; Bauer, Wolfgang.

Proceedings for ICPR 2010. ., 2010. p. 316-319 5597795.

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Kontschieder, P, Donoser, M, Bischof, H, Kritzinger, J & Bauer, W 2010, Detecting paper fibre cross sections in microtomy images. in Proceedings for ICPR 2010., 5597795, ., pp. 316-319, 20th International Conference on Pattern Recognition (ICPR), Istanbul, Turkey, 23/08/10. https://doi.org/10.1109/ICPR.2010.86
Kontschieder P, Donoser M, Bischof H, Kritzinger J, Bauer W. Detecting paper fibre cross sections in microtomy images. In Proceedings for ICPR 2010. . 2010. p. 316-319. 5597795 https://doi.org/10.1109/ICPR.2010.86
Kontschieder, Peter ; Donoser, Michael ; Bischof, Horst ; Kritzinger, Johannes ; Bauer, Wolfgang. / Detecting paper fibre cross sections in microtomy images. Proceedings for ICPR 2010. ., 2010. pp. 316-319
@inproceedings{7b82e62e45f143fd95706dbe8c5b3b29,
title = "Detecting paper fibre cross sections in microtomy images",
abstract = "The goal of this work is the fully-automated detection of cellulose fibre cross sections in microtomy images. A lack of significant appearance information makes edges the only reliable cue for detection. We present a novel and highly discriminative edge fragment descriptor that represents angular relations between fragment points. We train a Random Forest with a plurality of these descriptors including their respective center votes. In such a way, the Random Forest exploits the knowledge about the object centroid for detection using a generalized Hough voting scheme. In the experiments we found that our method is able to robustly detect fibre cross sections in microtomy images and can therefore serve as initialization for successive fibre segmentation or tracking algorithms.",
author = "Peter Kontschieder and Michael Donoser and Horst Bischof and Johannes Kritzinger and Wolfgang Bauer",
year = "2010",
doi = "10.1109/ICPR.2010.86",
language = "English",
isbn = "9780769541099",
pages = "316--319",
booktitle = "Proceedings for ICPR 2010",
publisher = ".",

}

TY - GEN

T1 - Detecting paper fibre cross sections in microtomy images

AU - Kontschieder, Peter

AU - Donoser, Michael

AU - Bischof, Horst

AU - Kritzinger, Johannes

AU - Bauer, Wolfgang

PY - 2010

Y1 - 2010

N2 - The goal of this work is the fully-automated detection of cellulose fibre cross sections in microtomy images. A lack of significant appearance information makes edges the only reliable cue for detection. We present a novel and highly discriminative edge fragment descriptor that represents angular relations between fragment points. We train a Random Forest with a plurality of these descriptors including their respective center votes. In such a way, the Random Forest exploits the knowledge about the object centroid for detection using a generalized Hough voting scheme. In the experiments we found that our method is able to robustly detect fibre cross sections in microtomy images and can therefore serve as initialization for successive fibre segmentation or tracking algorithms.

AB - The goal of this work is the fully-automated detection of cellulose fibre cross sections in microtomy images. A lack of significant appearance information makes edges the only reliable cue for detection. We present a novel and highly discriminative edge fragment descriptor that represents angular relations between fragment points. We train a Random Forest with a plurality of these descriptors including their respective center votes. In such a way, the Random Forest exploits the knowledge about the object centroid for detection using a generalized Hough voting scheme. In the experiments we found that our method is able to robustly detect fibre cross sections in microtomy images and can therefore serve as initialization for successive fibre segmentation or tracking algorithms.

UR - http://www.scopus.com/inward/record.url?scp=78149484673&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2010.86

DO - 10.1109/ICPR.2010.86

M3 - Conference contribution

SN - 9780769541099

SP - 316

EP - 319

BT - Proceedings for ICPR 2010

PB - .

ER -