Fast multiscale image segmentation Export

@inproceedings{citeulike:397619, abstract = {We introduce a fast, multiscale algorithm for image segmentation. Our algorithm uses modern numeric techniques to find an approximate solution to normalized cut measures in time that is linear in the size of the image with only a few dozen operations per pixel. In just one pass the algorithm provides a complete hierarchical decomposition of the image into segments. The algorithm detects the segments by applying a process of recursive coarsening in which the same minimization problem is represented with fewer and fewer variables producing an irregular pyramid. During this coarsening process we may compute additional internal statistics of the emerging segments and use these statistics to facilitate the segmentation process. Once the pyramid is completed it is scanned from the top down to associate pixels close to the boundaries of segments with the appropriate segment. The algorithm is inspired by algebraic multigrid (AMG) solvers of minimization problems of heat or electric networks. We demonstrate the algorithm by applying it to real images}, author = {Sharon, E. and Brandt, A. and Basri, R.}, citeulike-article-id = {397619}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/CVPR.2000.855801}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=855801}, doi = {10.1109/CVPR.2000.855801}, journal = {Computer Vision and Pattern Recognition, 2000. Proceedings. IEEE Conference on}, keywords = {analysis, image, resolution, scale, segmentation}, pages = {70--77 vol.1}, posted-at = {2006-02-03 14:24:58}, priority = {2}, title = {Fast multiscale image segmentation}, url = {http://dx.doi.org/10.1109/CVPR.2000.855801}, volume = {1}, year = {2000} }

TY - CONF ID - citeulike:397619 L3 - citeulike-article-id:397619 N2 - We introduce a fast, multiscale algorithm for image segmentation. Our algorithm uses modern numeric techniques to find an approximate solution to normalized cut measures in time that is linear in the size of the image with only a few dozen operations per pixel. In just one pass the algorithm provides a complete hierarchical decomposition of the image into segments. The algorithm detects the segments by applying a process of recursive coarsening in which the same minimization problem is represented with fewer and fewer variables producing an irregular pyramid. During this coarsening process we may compute additional internal statistics of the emerging segments and use these statistics to facilitate the segmentation process. Once the pyramid is completed it is scanned from the top down to associate pixels close to the boundaries of segments with the appropriate segment. The algorithm is inspired by algebraic multigrid (AMG) solvers of minimization problems of heat or electric networks. We demonstrate the algorithm by applying it to real images JF - Computer Vision and Pattern Recognition, 2000. Proceedings. IEEE Conference on EP - 77 vol.1 TI - Fast multiscale image segmentation VL - 1 SP - 70 KW - analysis KW - image KW - resolution KW - scale KW - segmentation AU - Sharon, E AU - Brandt, A AU - Basri, R PY - 2000/// UR - http://dx.doi.org/10.1109/CVPR.2000.855801 ER -