SCALP: Superpixels with Contour Adherence using Linear Path - Archive ouverte HAL Access content directly
Conference Papers Year :

SCALP: Superpixels with Contour Adherence using Linear Path

Abstract

Superpixel decomposition methods are generally used as a pre-processing step to speed up image processing tasks. They group the pixels of an image into homogeneous regions while trying to respect existing contours. For all state-of-the-art superpixel decomposition methods, a trade-off is made between 1) computational time, 2) adherence to image contours and 3) regularity and compactness of the decomposition. In this paper, we propose a fast method to compute Superpixels with Contour Adherence using Linear Path (SCALP) in an iterative clustering framework. The distance computed when trying to associate a pixel to a superpixel during the clustering is enhanced by considering the linear path to the superpixel barycenter. The proposed framework produces regular and compact superpixels that adhere to the image contours. We provide a detailed evaluation of SCALP on the standard Berkeley Segmentation Dataset. The obtained results outperform state-of-the-art methods in terms of standard superpixel and contour detection metrics.
Fichier principal
Vignette du fichier
Giraud_ICPR_2016.pdf (3.6 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01349569 , version 3 (20-09-2016)

Identifiers

  • HAL Id : hal-01349569 , version 3

Cite

Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis. SCALP: Superpixels with Contour Adherence using Linear Path. International Conference on Pattern Recognition (ICPR'16), Dec 2016, Cancun, Mexico. pp.2374-2379. ⟨hal-01349569⟩

Collections

CNRS
364 View
358 Download

Share

Gmail Facebook Twitter LinkedIn More