Affinity Fusion Graph-based Framework for Natural Image Segmentation
Authors:
- Yang ZhangYZYang Zhang
- Moyun LiuMLMoyun Liu
- Jingwu HeJHJingwu He
- Fei PanFPFei Pan
- Yanwen GuoYGYanwen Guo
Preprint
Abstract
This paper proposes an affinity fusion graph framework to effectively connect different graphs with highly discriminating power and nonlinearity for natural image segmentation. The proposed framework combines adjacency-graphs and kernel spectral clustering based graphs (KSC-graphs) according to a new definition named affinity nodes of multi-scale superpixels. These affinity nodes are selected based on a better affiliation of superpixels, namely subspace-preserving representation which is generated by sparse subspace clustering based on subspace pursuit. Then a KSC-graph is built via a novel kernel spectral clustering to explore the nonlinear relationships among these affinity nodes. Moreover, an adjacency-graph at each scale is constructed, which is further used to update the proposed KSC-graph at affinity nodes. The fusion graph is built across different scales, and it is partitioned to obtain final segmentation result. Experimental results on the Berkeley segmentation dataset and Microsoft Research Cambridge dataset show the superiority of our framework in comparison with the state-of-the-art methods. The code is available at https://github.com/Yangzhangcst/AF-graph.Keywords
All Related Versions
This publication has 26 references indexed in Scilit:
- Iterative image segmentation with feature driven heuristic four-color labelingPattern Recognition, 2018
- Unsupervised hierarchical image segmentation through fuzzy entropy maximizationPattern Recognition, 2017
- Voronoï region-based adaptive unsupervised color image segmentationPattern Recognition, 2017
- Image Segmentation Using Linked Mean-Shift Vectors and Global/Local AttributesIEEE Transactions on Circuits and Systems for Video Technology, 2016
- Constructing the L2-Graph for Robust Subspace Learning and Subspace ClusteringIEEE Transactions on Cybernetics, 2016
- An integrated similarity metric for graph-based color image segmentationMultimedia Tools and Applications, 2014
- A general kernelization framework for learning algorithms based on kernel PCANeurocomputing, 2010
- Efficient Graph-Based Image SegmentationInternational Journal of Computer Vision, 2004
- Mean shift: a robust approach toward feature space analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- Normalized cuts and image segmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000