CSDL Home IEEE Transactions on Pattern Analysis & Machine Intelligence 2010 vol.32 Issue No.05 - May
Issue No.05 - May (2010 vol.32)
Guangcan Liu , Shanghai Jiao Tong University, Shanghai
Zhouchen Lin , Microsoft Research Asia, Beijing
Yong Yu , The Chinese University of Hong Kong, Hong Kong
Xiaoou Tang , Shanghai Jiao Tong University, Shanghai
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TPAMI.2009.40
In this work, we address the problem of performing class-specific unsupervised object segmentation, i.e., automatic segmentation without annotated training images. Object segmentation can be regarded as a special data clustering problem where both class-specific information and local texture/color similarities have to be considered. To this end, we propose a hybrid graph model (HGM) that can make effective use of both symmetric and asymmetric relationship among samples. The vertices of a hybrid graph represent the samples and are connected by directed edges and/or undirected ones, which represent the asymmetric and/or symmetric relationship between them, respectively. When applied to object segmentation, vertices are superpixels, the asymmetric relationship is the conditional dependence of occurrence, and the symmetric relationship is the color/texture similarity. By combining the Markov chain formed by the directed subgraph and the minimal cut of the undirected subgraph, the object boundaries can be determined for each image. Using the HGM, we can conveniently achieve simultaneous segmentation and recognition by integrating both top-down and bottom-up information into a unified process. Experiments on 42 object classes (9,415 images in total) show promising results.
Segmentation, graph-theoretic methods, spectral clustering.
Guangcan Liu, Zhouchen Lin, Yong Yu, Xiaoou Tang, "Unsupervised Object Segmentation with a Hybrid Graph Model (HGM)", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.32, no. 5, pp. 910-924, May 2010, doi:10.1109/TPAMI.2009.40