Segmentation on statistical manifold with watershed transform Export

@proceedings{lee08seg, abstract = {A watershed transform and a graph partitioning are studied on statistical manifold. Statistical manifold is a 2D Riemannian manifold which is statistically defined by maps that transform a parameter domain onto a set of probability density functions (PDFs). Due to high dimensionality of PDFs, it is hard and computationally expensive to produce segmentation on statistical manifold. In this paper, we propose a method that generates super-pixels using watershed transform. Finding capturing basins on statistical manifold is not straightforward. Here, we create a local distance map using metric tensor defined on statistical manifold. Watershed transform is performed on this local distance map and provides super-pixels that significantly reduce the number of data points and thus make efficient clustering algorithms such as normalized cut (Ncut) feasible to work on. Experimental results show superiority of the proposed method over principal component analysis (PCA) based dimensionality reduction method.}, author = {Lee, San-Mook and Abbott, A. L. and Araman, P. A.}, booktitle = {Image Processing, 2008. ICIP 2008. 15th IEEE International Conference on}, citeulike-article-id = {4779965}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/ICIP.2008.4711832}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4711832}, doi = {10.1109/ICIP.2008.4711832}, journal = {Image Processing, 2008. ICIP 2008. 15th IEEE International Conference on}, keywords = {clustering, manifold, onur2009, segmentation}, pages = {625--628}, posted-at = {2009-06-08 18:52:20}, priority = {2}, title = {Segmentation on statistical manifold with watershed transform}, url = {http://dx.doi.org/10.1109/ICIP.2008.4711832}, year = {2008} }

TY - CONF ID - lee08seg L3 - citeulike-article-id:4779965 N2 - A watershed transform and a graph partitioning are studied on statistical manifold. Statistical manifold is a 2D Riemannian manifold which is statistically defined by maps that transform a parameter domain onto a set of probability density functions (PDFs). Due to high dimensionality of PDFs, it is hard and computationally expensive to produce segmentation on statistical manifold. In this paper, we propose a method that generates super-pixels using watershed transform. Finding capturing basins on statistical manifold is not straightforward. Here, we create a local distance map using metric tensor defined on statistical manifold. Watershed transform is performed on this local distance map and provides super-pixels that significantly reduce the number of data points and thus make efficient clustering algorithms such as normalized cut (Ncut) feasible to work on. Experimental results show superiority of the proposed method over principal component analysis (PCA) based dimensionality reduction method. JF - Image Processing, 2008. ICIP 2008. 15th IEEE International Conference on EP - 628 TI - Segmentation on statistical manifold with watershed transform T2 - Image Processing, 2008. ICIP 2008. 15th IEEE International Conference on SP - 625 KW - clustering KW - manifold KW - onur2009 KW - segmentation AU - Lee, San-Mook AU - Abbott, AL AU - Araman, PA PY - 2008/// UR - http://dx.doi.org/10.1109/ICIP.2008.4711832 ER -