Image clustering by hyper-graph regularized non-negative matrix factorization

• Published in: Neurocomputing (Amsterdam) Vol. 138; pp. 209 - 217
• Main Authors: Zeng, Kun, Yu, Jun, Li, Cuihua, You, Jane, Jin, Taisong
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 22.08.2014; Elsevier
• Subjects: Algorithms; Applied sciences; Artificial intelligence; Clustering; Computer science; control theory; systems; Computer systems and distributed systems. User interface; Data processing. List processing. Character string processing; Dimension reduction; Exact sciences and technology; Factorization; Graphs; Hyper-graph laplacian; Image clustering; Image processing; Information retrieval. Graph; Manifold regularization; Manifolds; Memory organisation. Data processing; Non-negative matrix factorization; Pattern recognition. Digital image processing. Computational geometry; Representations; Software; Theoretical computing; Hyper-graph laplacian; Dimension reduction; Image clustering; Non-negative matrix factorization; Manifold regularization; Cluster analysis; Laplace operator; Brain; Image recognition; Tree(graph); Image processing; Central nervous system; Matrix factorization; Encephalon; Geometrical structure; Multidimensional analysis; Graph connectivity; Semi-supervised learning; Computer vision; Image retrieval; Graph theory; Pattern recognition; Ordered graph; Laplacian; Image analysis; Non negative matrix; Content-based retrieval; Geometrical method; Reduced order model; Regularization; Indexing
• ISSN: 0925-2312; 1872-8286
• DOI: 10.1016/j.neucom.2014.01.043

Image clustering is a critical step for the applications of content-based image retrieval, image annotation and other high-level image processing. To achieve these tasks, it is essential to obtain proper representation of the images. Non-negative Matrix Factorization (NMF) learns a part-based representation of the data, which is in accordance with how the brain recognizes objects. Due to its psychological and physiological interpretation, NMF has been successfully applied in a wide range of application such as pattern recognition, image processing and computer vision. On the other hand, manifold learning methods discover intrinsic geometrical structure of the high dimension data space. Incorporating manifold regularizer to standard NMF framework leads to novel performance. In this paper, we proposed a novel algorithm, call Hyper-graph regularized Non-negative Matrix Factorization (HNMF) for this purpose. HNMF captures intrinsic geometrical structure by constructing a hyper-graph instead of a simple graph. Hyper-graph model considers high-order relationship of samples and outperforms simple graph model. Empirical experiments demonstrate the effectiveness of the proposed algorithm in comparison to the state-of-the-art algorithms, especially some related works based on NMF.