Hybrid superpixel segmentation

Yuan Liu, Shangqi Lai, Tianyi Du, Yizhou Yu

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review


Superpixel over-segment image into meaningful clusters so that pixels in each cluster belong to one object. Many state-of-art superpixel algorithms have to make trade-offs between different concerns. As a result, algorithms that can produce good result in some situations fail in another. In order to take advantage of different algorithms and at the same time avoid their limitation, we propose a new fusion approach based on an efficient lazy greedy optimization. It incorporates two different superpixel algorithms as its ancestors and produces a hybrid result. The result is then refined based on a novel energy function that consists of two terms. The region term uses histogram diffusion distance and enforces intra-region similarity from an overall perspective; the boundary term models interregion dissimilarity from a local perspective. In experiments, the result of proposed algorithm matches the best superpixel algorithm and shows outstanding performance over its ancestor algorithms in all the standard evaluation metrics.

Original languageEnglish
Title of host publication2015 International Conference on Image and Vision Computing New Zealand, IVCNZ 2015
PublisherIEEE, Institute of Electrical and Electronics Engineers
ISBN (Electronic)9781509003570
Publication statusPublished - 2016
Externally publishedYes
EventImage and Vision Computing New Zealand (IVCNZ) 2015 - Auckland, New Zealand
Duration: 23 Nov 201524 Nov 2015
Conference number: 30th
https://ieeexplore.ieee.org/xpl/conhome/7748304/proceeding (Proceedings)

Publication series

NameInternational Conference Image and Vision Computing New Zealand
ISSN (Print)2151-2191
ISSN (Electronic)2151-2205


ConferenceImage and Vision Computing New Zealand (IVCNZ) 2015
Abbreviated titleIVCNZ 2015
Country/TerritoryNew Zealand
Internet address

Cite this