Learning-Based Symmetry Detection in Natural Images - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2012

Learning-Based Symmetry Detection in Natural Images


In this work we propose a learning-based approach to sym- metry detection in natural images. We focus on ribbon-like structures, i.e. contours marking local and approximate reflection symmetry and make three contributions to improve their detection. First, we create and make publicly available a ground-truth dataset for this task by build- ing on the Berkeley Segmentation Dataset. Second, we extract features representing multiple complementary cues, such as grayscale structure, color, texture, and spectral clustering information. Third, we use super- vised learning to learn how to combine these cues, and employ MIL to accommodate the unknown scale and orientation of the symmetric struc- tures. We systematically evaluate the performance contribution of each individual component in our pipeline, and demonstrate that overall we consistently improve upon results obtained using existing alternatives.
Fichier principal
Vignette du fichier
TsogkasKokkinos_symmetry_ECCV12.pdf (8.16 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00856535 , version 1 (01-09-2013)


  • HAL Id : hal-00856535 , version 1


Stavros Tsogkas, Iasonas Kokkinos. Learning-Based Symmetry Detection in Natural Images. ECCV - 12th European Conference on Computer Vision, Oct 2012, Florence, Italy. pp.41-54. ⟨hal-00856535⟩
290 View
956 Download


Gmail Facebook Twitter LinkedIn More