Image segmentation by bilayer superpixel grouping

Michael Ying Yang*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

1 Citation (Scopus)


The task of image segmentation is to group image pixels into visually meaningful objects. It has long been a challenging problem in computer vision and image processing. In this paper we address the segmentation as a super pixel grouping problem. We propose a novel graph-based segmentation framework which is able to integrate different cues from bilayer super pixels simultaneously. The key idea is that segmentation is formulated as grouping a subset of super pixels that partitions a bilayer graph over super pixels, with graph edges encoding super pixel similarity. We first construct a bipartite graph incorporating super pixel cue and long-range cue. Furthermore, mid-range cue is also incorporated in a hybrid graph model. Segmentation is solved by spectral clustering. Our approach is fully automatic, bottom-up, and unsupervised. We evaluate our proposed framework by comparing it to other generic segmentation approaches on the state-of-the-art benchmark database.

Original languageEnglish
Title of host publicationPattern Recognition (ACPR), 2013 - 2nd IAPR Asian Conference
Number of pages5
Publication statusPublished - 1 Jan 2013
Event2nd IAPR Asian Conference on Pattern Recognition, ACPR 2013 - Okinawa, Japan
Duration: 5 Nov 20138 Nov 2013
Conference number: 2


Conference2nd IAPR Asian Conference on Pattern Recognition, ACPR 2013
Abbreviated titleACPR 2013
Internet address


  • Bilayer graph
  • Segmentation
  • Spectral clustering
  • Superpixel

Fingerprint Dive into the research topics of 'Image segmentation by bilayer superpixel grouping'. Together they form a unique fingerprint.

Cite this