Dynamic spectral residual superpixels

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

View graph of relations

Author(s)

  • Jianchao Zhang
  • Angelica I. Aviles-Rivero
  • Daniel Heydecker
  • Carola-Bibiane Schönlieb

Related Research Unit(s)

Detail(s)

Original languageEnglish
Article number107705
Journal / PublicationPattern Recognition
Volume112
Online published21 Oct 2020
Publication statusPublished - Apr 2021

Abstract

We consider the problem of segmenting an image into superpixels in the context of k-means clustering, in which we wish to decompose an image into local, homogeneous regions corresponding to the underlying objects. Our novel approach builds upon the widely used Simple Linear Iterative Clustering (SLIC), and incorporate a measure of objects’ structure based on the spectral residual of an image. Based on this combination, we propose a modified initialisation scheme and search metric, which keeps fine-details. This combination leads to better adherence to object boundaries, while preventing unnecessary segmentation of large, uniform areas, and remaining computationally tractable in comparison to other methods. We demonstrate through numerical and visual experiments that our approach outperforms the state-of-the-art techniques.

Research Area(s)

  • K-means, Segmentation, Spectral residual, Superpixels

Citation Format(s)

Dynamic spectral residual superpixels. / Zhang, Jianchao; Aviles-Rivero, Angelica I.; Heydecker, Daniel; Zhuang, Xiaosheng; Chan, Raymond; Schönlieb, Carola-Bibiane.

In: Pattern Recognition, Vol. 112, 107705, 04.2021.

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review