SCALP: Superpixels with Contour Adherence using Linear Path

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Giraud, Rémi, Ta, Vinh-Thong, Papadakis, Nicolas
Natura: Preprint
Pubblicazione: 2019
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908543807913984
author Giraud, Rémi
Ta, Vinh-Thong
Papadakis, Nicolas
author_facet Giraud, Rémi
Ta, Vinh-Thong
Papadakis, Nicolas
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_1903_07149
institution arXiv
publishDate 2019
record_format arxiv
spellingShingle SCALP: Superpixels with Contour Adherence using Linear Path
Giraud, Rémi
Ta, Vinh-Thong
Papadakis, Nicolas
Computer Vision and Pattern Recognition
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.
title SCALP: Superpixels with Contour Adherence using Linear Path
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/1903.07149