Segmentation using superpixels: A bipartite graph partitioning approach
- 1 June 2012
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
Grouping cues can affect the performance of segmentation greatly. In this paper, we show that superpixels (image segments) can provide powerful grouping cues to guide segmentation, where superpixels can be collected easily by (over)-segmenting the image using any reasonable existing segmentation algorithms. Generated by different algorithms with varying parameters, superpixels can capture diverse and multi-scale visual patterns of a natural image. Successful integration of the cues from a large multitude of superpixels presents a promising yet not fully explored direction. In this paper, we propose a novel segmentation framework based on bipartite graph partitioning, which is able to aggregate multi-layer superpixels in a principled and very effective manner. Computationally, it is tailored to unbalanced bipartite graph structure and leads to a highly efficient, linear-time spectral algorithm. Our method achieves significantly better performance on the Berkeley Segmentation Database compared to state-of-the-art techniques.Keywords
This publication has 22 references indexed in Scilit:
- Segmentation of Natural Images by Texture and Boundary CompressionInternational Journal of Computer Vision, 2011
- Interactive image segmentation using probabilistic hypergraphsPattern Recognition, 2010
- Unsupervised segmentation of natural images via lossy data compressionComputer Vision and Image Understanding, 2008
- Comparing clusteringsPublished by Association for Computing Machinery (ACM) ,2005
- Efficient Graph-Based Image SegmentationInternational Journal of Computer Vision, 2004
- Solving cluster ensemble problems by bipartite graph partitioningPublished by Association for Computing Machinery (ACM) ,2004
- Mean shift: a robust approach toward feature space analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- Unsupervised segmentation of color-texture regions in images and videoIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001
- Bipartite graph partitioning and data clusteringPublished by Association for Computing Machinery (ACM) ,2001
- Normalized cuts and image segmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000