{"id":242,"date":"2019-10-23T08:10:30","date_gmt":"2019-10-23T08:10:30","guid":{"rendered":"http:\/\/www.cs.ubbcluj.ro\/~meco\/?p=242"},"modified":"2026-02-01T12:09:22","modified_gmt":"2026-02-01T12:09:22","slug":"autonomous-image-segmentation-by-competitive-unsupervised-growcut","status":"publish","type":"post","link":"https:\/\/www.cs.ubbcluj.ro\/~meco\/autonomous-image-segmentation-by-competitive-unsupervised-growcut\/","title":{"rendered":"Autonomous image segmentation by Competitive Unsupervised GrowCut (2019)"},"content":{"rendered":"\n<h3 class=\"wp-block-heading\">Abstract<\/h3>\n\n\n\n<p>In this paper, we introduce Competitive Unsupervised GrowCut, a cellular automata-based, unsupervised and autonomous algorithm that combines the label merging component of Unsupervised GrowCut with the soft label propagation mechanism of GrowCut. We evaluated our algorithm on two benchmark image segmentation datasets, along with two related methods proposed in the literature. We also provide a detailed comparative analysis of the three algorithms\u2019 segmentation performance and properties. Our analysis identified application-specific regimes that govern the relative performance of the analyzed algorithms.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">Citare<\/h3>\n\n\n\n<p>Marginean, R., Andreica, A., Diosan, L., Balint, Z., Autonomous image segmentation by Competitive Unsupervised GrowCut&nbsp;, SYNASC 2019, 2019, accepted<\/p>\n","protected":false},"excerpt":{"rendered":"<p>In this paper, we introduce Competitive Unsupervised GrowCut, a cellular automata-based, unsupervised and autonomous algorithm that combines the label merging component of Unsupervised GrowCut with the soft label propagation mechanism of GrowCut. We evaluated our algorithm on two benchmark image segmentation datasets, along with two related methods proposed in the literature. We also provide a detailed comparative analysis of the three algorithms\u2019 segmentation performance and properties. Our analysis identified application-specific regimes that govern the relative performance of the analyzed algorithms.<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[4],"tags":[10,11],"_links":{"self":[{"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/posts\/242"}],"collection":[{"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/comments?post=242"}],"version-history":[{"count":3,"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/posts\/242\/revisions"}],"predecessor-version":[{"id":1557,"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/posts\/242\/revisions\/1557"}],"wp:attachment":[{"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/media?parent=242"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/categories?post=242"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/tags?post=242"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}