Litcius/Paper detail

Hypergraph Clustering Using a New Laplacian Tensor with Applications in Image Processing

Jingya Chang, Yannan Chen, Liqun Qi, Hong Yan

2020SIAM Journal on Imaging Sciences27 citationsDOIOpen Access PDF

Abstract

In this paper, we consider the multiclass clustering problem involving a hypergraph model. Fundamentally, we study a new normalized Laplacian tensor of an even-uniform weighted hypergraph. The hypergraph's connectivity is related with the second smallest Z-eigenvalue of the proposed Laplacian tensor. Particularly, an analogue of fractional Cheeger inequality holds. Next, we generalize the Laplacian tensor based approach from biclustering to multiclass clustering. A tensor optimization model with an orthogonal constraint is established and analyzed. Finally, we apply our hypergraph clustering approach to image segmentation and motion segmentation problems. Experimental results demonstrate that our method is effective.

Topics & Concepts

HypergraphCluster analysisMathematicsTensor (intrinsic definition)Laplace operatorPattern recognition (psychology)Constraint (computer-aided design)Spectral clusteringArtificial intelligenceComputer scienceCombinatoricsPure mathematicsMathematical analysisGeometryTensor decomposition and applicationsMedical Image Segmentation TechniquesSparse and Compressive Sensing Techniques