Automatic graph extraction from color images

T. Lourens, Hiroshi G. Okuno, H. Kitano

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

1 Citation (Scopus)

Abstract

An approach to symbolic contour extraction is described that consists of three stages: enhancement, detection, and extraction of contours and corners. Contours and corners are enhanced by models of monkey cortical complex and endstopped cells. Detection of corners and local contour maxima is performed by selection of local maxima in both contour and corner enhanced images. These maxima form the anchor points of a greedy contour following algorithm that extracts the contours. This algorithm is based on the idea of spatially linking neurons along a contour that fire in synchrony to indicate an extracted contour. The extracted contours and detected corners represent the symbolic representation of the image. The advantage of the proposed model over other models is that the same low constant thresholds for corner and local contour maxima detection are used for different images. Closed contours are guaranteed by the contour following algorithm to yield a fully symbolic representation which is more suitable for reasoning and recognition. In this respect our methodology is unique, and clearly different from the standard (edge) contour detection methods. The results of the extracted contours (when displayed as being detected) show similar or better results compared to the SUSAN and Canny-CSS detectors.

Original languageEnglish
Title of host publicationProceedings - 11th International Conference on Image Analysis and Processing, ICIAP 2001
PublisherIEEE Computer Society
Pages302-308
Number of pages7
ISBN (Print)076951183X, 9780769511832
DOIs
Publication statusPublished - 2001
Externally publishedYes
Event11th International Conference on Image Analysis and Processing, ICIAP 2001 - Palermo
Duration: 2001 Sep 262001 Sep 28

Other

Other11th International Conference on Image Analysis and Processing, ICIAP 2001
CityPalermo
Period01/9/2601/9/28

Fingerprint

Color
Anchors
Neurons
Fires
Detectors

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Lourens, T., Okuno, H. G., & Kitano, H. (2001). Automatic graph extraction from color images. In Proceedings - 11th International Conference on Image Analysis and Processing, ICIAP 2001 (pp. 302-308). [957026] IEEE Computer Society. https://doi.org/10.1109/ICIAP.2001.957026

Automatic graph extraction from color images. / Lourens, T.; Okuno, Hiroshi G.; Kitano, H.

Proceedings - 11th International Conference on Image Analysis and Processing, ICIAP 2001. IEEE Computer Society, 2001. p. 302-308 957026.

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

Lourens, T, Okuno, HG & Kitano, H 2001, Automatic graph extraction from color images. in Proceedings - 11th International Conference on Image Analysis and Processing, ICIAP 2001., 957026, IEEE Computer Society, pp. 302-308, 11th International Conference on Image Analysis and Processing, ICIAP 2001, Palermo, 01/9/26. https://doi.org/10.1109/ICIAP.2001.957026
Lourens T, Okuno HG, Kitano H. Automatic graph extraction from color images. In Proceedings - 11th International Conference on Image Analysis and Processing, ICIAP 2001. IEEE Computer Society. 2001. p. 302-308. 957026 https://doi.org/10.1109/ICIAP.2001.957026
Lourens, T. ; Okuno, Hiroshi G. ; Kitano, H. / Automatic graph extraction from color images. Proceedings - 11th International Conference on Image Analysis and Processing, ICIAP 2001. IEEE Computer Society, 2001. pp. 302-308
@inproceedings{9dc6abdc36054260a9cc96c5897d252c,
title = "Automatic graph extraction from color images",
abstract = "An approach to symbolic contour extraction is described that consists of three stages: enhancement, detection, and extraction of contours and corners. Contours and corners are enhanced by models of monkey cortical complex and endstopped cells. Detection of corners and local contour maxima is performed by selection of local maxima in both contour and corner enhanced images. These maxima form the anchor points of a greedy contour following algorithm that extracts the contours. This algorithm is based on the idea of spatially linking neurons along a contour that fire in synchrony to indicate an extracted contour. The extracted contours and detected corners represent the symbolic representation of the image. The advantage of the proposed model over other models is that the same low constant thresholds for corner and local contour maxima detection are used for different images. Closed contours are guaranteed by the contour following algorithm to yield a fully symbolic representation which is more suitable for reasoning and recognition. In this respect our methodology is unique, and clearly different from the standard (edge) contour detection methods. The results of the extracted contours (when displayed as being detected) show similar or better results compared to the SUSAN and Canny-CSS detectors.",
author = "T. Lourens and Okuno, {Hiroshi G.} and H. Kitano",
year = "2001",
doi = "10.1109/ICIAP.2001.957026",
language = "English",
isbn = "076951183X",
pages = "302--308",
booktitle = "Proceedings - 11th International Conference on Image Analysis and Processing, ICIAP 2001",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Automatic graph extraction from color images

AU - Lourens, T.

AU - Okuno, Hiroshi G.

AU - Kitano, H.

PY - 2001

Y1 - 2001

N2 - An approach to symbolic contour extraction is described that consists of three stages: enhancement, detection, and extraction of contours and corners. Contours and corners are enhanced by models of monkey cortical complex and endstopped cells. Detection of corners and local contour maxima is performed by selection of local maxima in both contour and corner enhanced images. These maxima form the anchor points of a greedy contour following algorithm that extracts the contours. This algorithm is based on the idea of spatially linking neurons along a contour that fire in synchrony to indicate an extracted contour. The extracted contours and detected corners represent the symbolic representation of the image. The advantage of the proposed model over other models is that the same low constant thresholds for corner and local contour maxima detection are used for different images. Closed contours are guaranteed by the contour following algorithm to yield a fully symbolic representation which is more suitable for reasoning and recognition. In this respect our methodology is unique, and clearly different from the standard (edge) contour detection methods. The results of the extracted contours (when displayed as being detected) show similar or better results compared to the SUSAN and Canny-CSS detectors.

AB - An approach to symbolic contour extraction is described that consists of three stages: enhancement, detection, and extraction of contours and corners. Contours and corners are enhanced by models of monkey cortical complex and endstopped cells. Detection of corners and local contour maxima is performed by selection of local maxima in both contour and corner enhanced images. These maxima form the anchor points of a greedy contour following algorithm that extracts the contours. This algorithm is based on the idea of spatially linking neurons along a contour that fire in synchrony to indicate an extracted contour. The extracted contours and detected corners represent the symbolic representation of the image. The advantage of the proposed model over other models is that the same low constant thresholds for corner and local contour maxima detection are used for different images. Closed contours are guaranteed by the contour following algorithm to yield a fully symbolic representation which is more suitable for reasoning and recognition. In this respect our methodology is unique, and clearly different from the standard (edge) contour detection methods. The results of the extracted contours (when displayed as being detected) show similar or better results compared to the SUSAN and Canny-CSS detectors.

UR - http://www.scopus.com/inward/record.url?scp=0347345737&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0347345737&partnerID=8YFLogxK

U2 - 10.1109/ICIAP.2001.957026

DO - 10.1109/ICIAP.2001.957026

M3 - Conference contribution

SN - 076951183X

SN - 9780769511832

SP - 302

EP - 308

BT - Proceedings - 11th International Conference on Image Analysis and Processing, ICIAP 2001

PB - IEEE Computer Society

ER -