Skip to Main content Skip to Navigation
Conference papers

Highly Accurate Boundary Detection and Grouping

Abstract : In this work we address boundary detection and boundary grouping. We first pursue a learning- based approach to boundary detection. For this (i) we leverage appearance and context information by extracting descriptors around edgels and use them as features for classification, (ii) we use discrimina- tive dimensionality reduction for efficiency and (iii) we use outlier-resilient boosting to deal with noise in the training set. We then introduce fractional-linear programming to optimize a grouping criterion that is expressed as a cost ratio. Our contributions are systematically evaluated on the Berkeley benchmark.
Document type :
Conference papers
Complete list of metadata

https://hal.inria.fr/hal-00857481
Contributor : Iasonas Kokkinos <>
Submitted on : Tuesday, September 3, 2013 - 3:46:06 PM
Last modification on : Wednesday, April 8, 2020 - 3:28:32 PM

Identifiers

  • HAL Id : hal-00857481, version 1

Collections

Citation

Iasonas Kokkinos. Highly Accurate Boundary Detection and Grouping. CVPR - IEEE Conf. on Computer Vision and Pattern Recognition, 2010, San Francisco, United States. pp.2520-2527. ⟨hal-00857481⟩

Share

Metrics

Record views

197