Supervised learning of edges and object boundaries
Research output: Contribution to journal › Conference article › Research › peer-review
Standard
Supervised learning of edges and object boundaries. / Dollár, Piotr; Tu, Zhuowen; Belongie, Serge.
In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2006, p. 1964-1971.Research output: Contribution to journal › Conference article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Supervised learning of edges and object boundaries
AU - Dollár, Piotr
AU - Tu, Zhuowen
AU - Belongie, Serge
PY - 2006
Y1 - 2006
N2 - Edge detection is one of the most studied problems in computer vision, yet it remains a very challenging task. It is difficult since often the decision for an edge cannot be made purely based on low level cues such as gradient, instead we need to engage all levels of information, low, middle, and high, in order to decide where to put edges. In this paper we propose a novel supervised learning algorithm for edge and object boundary detection which we refer to as Boosted Edge Learning or BEL for short. A decision of an edge point is made independently at each location in the image; a very large aperture is used providing significant context for each decision. In the learning stage, the algorithm selects and combines a large number of features across different scales in order to learn a discriminative model using an extended version of the Probabilistic Boosting Tree classification algorithm. The learning based framework is highly adaptive and there are no parameters to tune. We show applications for edge detection in a number of specific image domains as well as on natural images. We test on various datasets including the Berkeley dataset and the results obtained are very good.
AB - Edge detection is one of the most studied problems in computer vision, yet it remains a very challenging task. It is difficult since often the decision for an edge cannot be made purely based on low level cues such as gradient, instead we need to engage all levels of information, low, middle, and high, in order to decide where to put edges. In this paper we propose a novel supervised learning algorithm for edge and object boundary detection which we refer to as Boosted Edge Learning or BEL for short. A decision of an edge point is made independently at each location in the image; a very large aperture is used providing significant context for each decision. In the learning stage, the algorithm selects and combines a large number of features across different scales in order to learn a discriminative model using an extended version of the Probabilistic Boosting Tree classification algorithm. The learning based framework is highly adaptive and there are no parameters to tune. We show applications for edge detection in a number of specific image domains as well as on natural images. We test on various datasets including the Berkeley dataset and the results obtained are very good.
UR - http://www.scopus.com/inward/record.url?scp=33845580709&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2006.298
DO - 10.1109/CVPR.2006.298
M3 - Conference article
AN - SCOPUS:33845580709
SP - 1964
EP - 1971
JO - I E E E Conference on Computer Vision and Pattern Recognition. Proceedings
JF - I E E E Conference on Computer Vision and Pattern Recognition. Proceedings
SN - 1063-6919
T2 - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006
Y2 - 17 June 2006 through 22 June 2006
ER -
ID: 302053645