Abstract Traditional hypergraph-based image classification methods overlook the correlation among hyperedges in hypergraph construction, which results in poor classification performance. A method based on hyperedge correlation is proposed in this paper. The correlation among hyperedses is quantified by combining the image vision and its corresponding tags information. The tags corresponding to the image are introduced into the image classification as indicator information and thus better classification performance is obtained. The effectiveness of the proposed method is verified by experiments conducted on datasets such as LabelMe and UIUC.
[1] Guillaumin M, Verbeek J, Schmid C. Multimodal Semi-Supervised Learning for Image Classification // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. San Francisco, USA, 2010: 902-909 [2] Zhu Y, Chen Y Q, Lu Z Q, et al. Heterogeneous Transfer Learning for Image Classification // Proc of the 25th AAAI Conference on Artificial Intelligence. San Francisco, USA, 2011: 1034-1039 [3] Wang G, Hoiem D, Forsyth D. Building Text Features for Object Image Classification // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Miami, USA, 2009: 1367-1374 [4] Wang C, Blei D, Li F F. Simultaneous Image Classification and Annotation // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Miami, USA, 2009: 1903-1910 [5] Agarwal S, Lim J, Manor L, et al. Beyond Pairwise Clustering // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. San Diego, USA, 2005: 838-845 [6] Sun L, Ji S W, Ye J P. Hypergraph Spectral Learning for Multi-label Classification // Proc of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA, 2008: 668-676 [7] Tian Z, Hwang T H, Kuang R. A Hyprgraph-Based Learning Algorithm for Classifying Gene Expression and ArrayCGH Data with Prior Knowledge. Bioinformatics, 2009, 25(21): 2831-2838 [8] Zhou D Y, Huang J Y, Sch lkopf B. Learning with Hypergraphs: Clustering, Classification and Embedding // Proc of the Annual Conference on Neural Information Processing Systems. Vancouver, Canada, 2006: 1601-1608 [9] Agarwal S, Branson K, Belongie S. Higher Order Learning with Graphs // Proc of the International Conference on Machine Learning. Pittsburgh, USA, 2006: 17-24 [10] Huang Y C, Liu Q S, Zhang S T, et al. Image Retrieval via Probabilistic Hypergraph Ranking // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. San Francisco, USA, 2010: 3376-3383 [11] Yu J, Tao D C, Wang M. Adaptive Hypergraph Learning and Its Application in Image Classification. IEEE Trans on Image Processing, 2012, 21(7): 3262-3272 [12] Lu Z W, Peng Y X. Combining Latent Semantic Learning and Reduced Hypergraph Learning for Semi-Supervised Image Categorization // Proc of the 19th ACM International Conference on Multimedia. New York, USA, 2011: 1409-1412 [13] Gao Y, Wang M, Luan H B, et al. Tag-Based Social Image Search with Visual-Text Join Hypergraph Learning // Proc of the 19th ACM International Conference on Multimedia. New York, USA, 2011: 1517-1520 [14] Huang Y C, Liu Q S, Lü F J, et al. Unsupervised Image Categorization by Hypergraph Partition. IEEE Trans on Pattern Analysis and Machine Intelligence, 2011, 33 (6): 1266-1273 [15] Liu D, Hua X S, Yang L J, et al. Tag Ranking // Proc of the 18th International Conference on World Wide Web. New York, USA, 2009: 351-360 [16] Cilibrasi R, Vitanyi P. The Google Similarity Distance. IEEE Trans on Knowledge and Data Engineering, 2007, 19(3): 370-383
2014, Vol. 27 
