Global Similarity with Additive Smoothness for Spectral Segmentation

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedings – Annual report year: 2019Researchpeer-review



View graph of relations

Faithful representation of pairwise pixel affinities is crucial for the outcome of spectral segmentation methods. In conventional affinity models only close-range pixels interact, and a variety of subsequent techniques aims at faster propagation of local grouping cues across longrange connections. In this paper we propose a general framework for constructing a full-range affinity matrix. Our affinity matrix consists of a global similarity matrix and an additive proximity matrix. The similarity in appearance, including intensity and texture, is encoded for each pair of image pixels. Despite being full-range, our similarity matrix has a simple decomposition, which exploits an assignment of image pixels to dictionary elements. The additive proximity enforces smoothness to the segmentation by imposing interactions between near-by pixels. Our approach allows us to assess the advantages of using a full-range affinity for various spectral segmentation problems. Within our general framework we develop a few variants of full affinity for experimental validation. The performance we accomplish on composite textured images is excellent, and the results on natural images are promising.
Original languageEnglish
Title of host publicationScale Space and Variational Methods in Computer Vision
Publication date2019
ISBN (Print)978-3-030-22367-0
Publication statusPublished - 2019
Event7th International Conference on Scale Space and Variational Methods in Computer Vision - Evangelische Tagungsstätte Hofgeismar, Hofgeismar, Germany
Duration: 30 Jun 20194 Jul 2019


Conference7th International Conference on Scale Space and Variational Methods in Computer Vision
LocationEvangelische Tagungsstätte Hofgeismar
SeriesLecture Notes in Computer Science
CitationsWeb of Science® Times Cited: No match on DOI

    Research areas

  • Image segmentation, Spectral methods, Affinity matrix

Download statistics

No data available

ID: 182433138