{"id":4194,"date":"2025-10-26T15:05:53","date_gmt":"2025-10-26T15:05:53","guid":{"rendered":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/?page_id=4194"},"modified":"2025-10-26T15:05:53","modified_gmt":"2025-10-26T15:05:53","slug":"hybrid-super-voxel-segmentation-graph-cuts-fuzzy-c-means","status":"publish","type":"page","link":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/?page_id=4194","title":{"rendered":"Hybrid Super-Voxel Segmentation: Graph Cuts + Fuzzy C-Means"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\">We propose a hybrid super-voxel segmentation pipeline that combines soft memberships from fuzzy<br>c-means (FCM) with spatial regularization via graph cuts on a region adjacency graph (RAG). Our hybrid<br>achieves 0.70 mean IoU at 42 fps (synthetic), outperforming SLIC-only (0.55) and FCM-only (0.52)<br>under the same budget. The result is spatially coherent clusters that respect object boundaries while<br>preserving soft assignment information at real-time performance.<\/p>\n\n\n\n<div data-wp-interactive=\"core\/file\" class=\"wp-block-file\"><object data-wp-bind--hidden=\"!state.hasPdfPreview\" hidden class=\"wp-block-file__embed\" data=\"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/wp-content\/uploads\/2025\/10\/Hybrid-Super-Voxel-Segmentation-Rev-2.pdf\" type=\"application\/pdf\" style=\"width:100%;height:600px\" aria-label=\"Embed of Hybrid Super-Voxel Segmentation Rev 2.\"><\/object><a id=\"wp-block-file--media-36a88bba-e5a9-4b4f-b27c-b7d0daf5d0db\" href=\"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/wp-content\/uploads\/2025\/10\/Hybrid-Super-Voxel-Segmentation-Rev-2.pdf\">Hybrid Super-Voxel Segmentation Rev 2<\/a><a href=\"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/wp-content\/uploads\/2025\/10\/Hybrid-Super-Voxel-Segmentation-Rev-2.pdf\" class=\"wp-block-file__button wp-element-button\" download aria-describedby=\"wp-block-file--media-36a88bba-e5a9-4b4f-b27c-b7d0daf5d0db\">Download<\/a><\/div>\n\n\n\n<pre class=\"wp-block-code\"><code>@article{Achanta2012SLIC,\n  title={SLIC Superpixels Compared to State-of-the-art Superpixel Methods},\n  author={Achanta, Radhakrishna and Shaji, Appu and Smith, Kevin and Lucchi, Aur{\\'e}lien and Fua, Pascal and S{\\\"u}sstrunk, Sabine},\n  journal={IEEE TPAMI},\n  year={2012}, volume={34}, number={11}, pages={2274--2282}\n}\n\n@book{Bezdek1981FCM,\n  title = {Pattern Recognition with Fuzzy Objective Function Algorithms},\n  author = {Bezdek, James C.},\n  year = {1981}, publisher = {Springer}\n}\n\n@inproceedings{Boykov2001ICCV,\n  title={Interactive Graph Cuts for Optimal Boundary \\&amp; Region Segmentation of Objects in N-D Images},\n  author={Boykov, Yuri and Jolly, Marie-Pierre},\n  booktitle={ICCV}, year={2001}, pages={105--112}\n}\n\n@article{Boykov2001PAMI,\n  title={Fast Approximate Energy Minimization via Graph Cuts},\n  author={Boykov, Yuri and Veksler, Olga and Zabih, Ramin},\n  journal={IEEE TPAMI}, year={2001}, volume={23}, number={11}, pages={1222--1239}\n}\n\n@article{ShiMalik2000PAMI,\n  title={Normalized Cuts and Image Segmentation},\n  author={Shi, Jianbo and Malik, Jitendra},\n  journal={IEEE TPAMI}, year={2000}, volume={22}, number={8}, pages={888--905}\n}\n\n@article{Felzenszwalb2004IJCV,\n  title={Efficient Graph-Based Image Segmentation},\n  author={Felzenszwalb, Pedro F. and Huttenlocher, Daniel P.},\n  journal={IJCV}, year={2004}, volume={59}, number={2}, pages={167--181}\n}\n\n@article{skimage2014,\n  title={scikit-image: image processing in {P}ython},\n  author={van der Walt, St{\\'e}fan and Sch{\\\"o}nberger, Johannes L. and Nunez-Iglesias, Juan and Boulogne, Fran{\\c{c}}ois and Warner, Joshua D. and others},\n  journal={PeerJ}, year={2014}, volume={2}, pages={e453}\n}<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"<p>We propose a hybrid super-voxel segmentation pipeline that combines soft memberships from fuzzyc-means (FCM) with spatial regularization via graph cuts on a region adjacency graph (RAG). Our hybridachieves 0.70 mean IoU at 42 fps (synthetic), outperforming SLIC-only (0.55) and FCM-only (0.52)under the same budget. The result is spatially coherent clusters that respect object boundaries whilepreserving&hellip;&nbsp;<\/p>\n","protected":false},"author":2,"featured_media":2852,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"neve_meta_sidebar":"","neve_meta_container":"","neve_meta_enable_content_width":"","neve_meta_content_width":0,"neve_meta_title_alignment":"","neve_meta_author_avatar":"","neve_post_elements_order":"","neve_meta_disable_header":"","neve_meta_disable_footer":"","neve_meta_disable_title":"","footnotes":""},"class_list":["post-4194","page","type-page","status-publish","has-post-thumbnail","hentry"],"_links":{"self":[{"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/pages\/4194","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=4194"}],"version-history":[{"count":0,"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/pages\/4194\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/media\/2852"}],"wp:attachment":[{"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4194"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}