Active contour with selective local or global segmentation for intensity inhomogeneous image

Thi Thao Tran, Van Truong Pham, Yun Jen Chiu, Kuo Kai Shyu

研究成果: 書貢獻/報告類型會議論文篇章同行評審

12 引文 斯高帕斯(Scopus)

摘要

In this paper, a novel algorithm for intensity inhomogeneous image segmentation is proposed. The presented method introduces a signed pressure force function using the local information of the image to be segmented. Thus, this model can work with heterogeneous images. In addition, by taking the advantages of Geodesic active contour (GAC) and Chan-Vese (C-V) model, the mehod could deal with objects even with discrete Iblur boundaries and gives exact results in detecting object boundaries. Experimental results demonstrate that the proposed model is effective in segmenting inhomogeneous images and promising in pattern recognition.

原文???core.languages.en_GB???
主出版物標題Proceedings - 2010 3rd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2010
頁面306-310
頁數5
DOIs
出版狀態已出版 - 2010
事件2010 3rd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2010 - Chengdu, China
持續時間: 9 7月 201011 7月 2010

出版系列

名字Proceedings - 2010 3rd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2010
1

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???2010 3rd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2010
國家/地區China
城市Chengdu
期間9/07/1011/07/10

指紋

深入研究「Active contour with selective local or global segmentation for intensity inhomogeneous image」主題。共同形成了獨特的指紋。

引用此