Discriminative generative contour detection

Chao Zhang, Xiong Li, Xiang Ruan, Yuming Zhao, Ming Hsuan Yang

Research output: Contribution to conferencePaper

7 Citations (Scopus)

Abstract

Contour detection is an important and fundamental problem in computer vision which finds numerous applications. Despite significant progress has been made in the past decades, contour detection from natural images remains a challenging task due to the difficulty of clearly distinguishing between edges of objects and surrounding backgrounds. To address this problem, we first capture multi-scale features from pixel-level to segmentlevel using local and global information. These features are mapped to a space where discriminative information is captured by computing posterior divergence of Gaussian mixture models and then used to train a random forest classifier for contour detection. We evaluate the proposed algorithm against leading methods in the literature on the Berkeley segmentation and Weizmann horse data sets. Experimental results demonstrate that the proposed contour detection algorithm performs favorably against state-of-the-art methods in terms of speed and accuracy.

Original languageEnglish
DOIs
Publication statusPublished - 2013 Jan 1
Event2013 24th British Machine Vision Conference, BMVC 2013 - Bristol, United Kingdom
Duration: 2013 Sep 92013 Sep 13

Conference

Conference2013 24th British Machine Vision Conference, BMVC 2013
CountryUnited Kingdom
CityBristol
Period13/9/913/9/13

Fingerprint

Computer vision
Classifiers
Pixels

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Cite this

Zhang, C., Li, X., Ruan, X., Zhao, Y., & Yang, M. H. (2013). Discriminative generative contour detection. Paper presented at 2013 24th British Machine Vision Conference, BMVC 2013, Bristol, United Kingdom. https://doi.org/10.5244/C.27.74
Zhang, Chao ; Li, Xiong ; Ruan, Xiang ; Zhao, Yuming ; Yang, Ming Hsuan. / Discriminative generative contour detection. Paper presented at 2013 24th British Machine Vision Conference, BMVC 2013, Bristol, United Kingdom.
@conference{b9418396ee9c48a399cb7185cfebd7c2,
title = "Discriminative generative contour detection",
abstract = "Contour detection is an important and fundamental problem in computer vision which finds numerous applications. Despite significant progress has been made in the past decades, contour detection from natural images remains a challenging task due to the difficulty of clearly distinguishing between edges of objects and surrounding backgrounds. To address this problem, we first capture multi-scale features from pixel-level to segmentlevel using local and global information. These features are mapped to a space where discriminative information is captured by computing posterior divergence of Gaussian mixture models and then used to train a random forest classifier for contour detection. We evaluate the proposed algorithm against leading methods in the literature on the Berkeley segmentation and Weizmann horse data sets. Experimental results demonstrate that the proposed contour detection algorithm performs favorably against state-of-the-art methods in terms of speed and accuracy.",
author = "Chao Zhang and Xiong Li and Xiang Ruan and Yuming Zhao and Yang, {Ming Hsuan}",
year = "2013",
month = "1",
day = "1",
doi = "10.5244/C.27.74",
language = "English",
note = "2013 24th British Machine Vision Conference, BMVC 2013 ; Conference date: 09-09-2013 Through 13-09-2013",

}

Zhang, C, Li, X, Ruan, X, Zhao, Y & Yang, MH 2013, 'Discriminative generative contour detection', Paper presented at 2013 24th British Machine Vision Conference, BMVC 2013, Bristol, United Kingdom, 13/9/9 - 13/9/13. https://doi.org/10.5244/C.27.74

Discriminative generative contour detection. / Zhang, Chao; Li, Xiong; Ruan, Xiang; Zhao, Yuming; Yang, Ming Hsuan.

2013. Paper presented at 2013 24th British Machine Vision Conference, BMVC 2013, Bristol, United Kingdom.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Discriminative generative contour detection

AU - Zhang, Chao

AU - Li, Xiong

AU - Ruan, Xiang

AU - Zhao, Yuming

AU - Yang, Ming Hsuan

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Contour detection is an important and fundamental problem in computer vision which finds numerous applications. Despite significant progress has been made in the past decades, contour detection from natural images remains a challenging task due to the difficulty of clearly distinguishing between edges of objects and surrounding backgrounds. To address this problem, we first capture multi-scale features from pixel-level to segmentlevel using local and global information. These features are mapped to a space where discriminative information is captured by computing posterior divergence of Gaussian mixture models and then used to train a random forest classifier for contour detection. We evaluate the proposed algorithm against leading methods in the literature on the Berkeley segmentation and Weizmann horse data sets. Experimental results demonstrate that the proposed contour detection algorithm performs favorably against state-of-the-art methods in terms of speed and accuracy.

AB - Contour detection is an important and fundamental problem in computer vision which finds numerous applications. Despite significant progress has been made in the past decades, contour detection from natural images remains a challenging task due to the difficulty of clearly distinguishing between edges of objects and surrounding backgrounds. To address this problem, we first capture multi-scale features from pixel-level to segmentlevel using local and global information. These features are mapped to a space where discriminative information is captured by computing posterior divergence of Gaussian mixture models and then used to train a random forest classifier for contour detection. We evaluate the proposed algorithm against leading methods in the literature on the Berkeley segmentation and Weizmann horse data sets. Experimental results demonstrate that the proposed contour detection algorithm performs favorably against state-of-the-art methods in terms of speed and accuracy.

UR - http://www.scopus.com/inward/record.url?scp=84898422772&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898422772&partnerID=8YFLogxK

U2 - 10.5244/C.27.74

DO - 10.5244/C.27.74

M3 - Paper

AN - SCOPUS:84898422772

ER -

Zhang C, Li X, Ruan X, Zhao Y, Yang MH. Discriminative generative contour detection. 2013. Paper presented at 2013 24th British Machine Vision Conference, BMVC 2013, Bristol, United Kingdom. https://doi.org/10.5244/C.27.74