Kim, Sunhee Park, Sehyung Lee, Deukhee Kim, Youngjun 2024-01-19T11:39:15Z 2024-01-19T11:39:15Z 2022-03-01 2015-08 1557-170X https://pubs.kist.re.kr/handle/201004/115027 This paper presents a new active contour segmentation model using a level set function that can correctly capture both the strong and the weak boundaries of a target enclosed by bright and dark regions at the same time. We introduce an enhanced image obtained from prior information about the intensity of the target. The enhanced image emphasizes the regions where pixels have intensities close to the prior intensity. This enables a desirable segmentation of an image having a partially low contrast with the target surrounded by regions that are brighter or darker than the target. We define an edge indicator function on an original image, and local and regularization forces on an enhanced image. An edge indicator function and two forces are incorporated in order to identify the strong and weak boundaries, respectively. We established an evolution equation of contours in the level set formulation and experimented with several medical images to show the performance of the proposed method. English IEEE Active Contour Segmentation Using Level Set Function with Enhanced Image from Prior Intensity Conference 1 37th Annual International Conference of the IEEE-Engineering-in-Medicine-and-Biology-Society (EMBC), pp.3069 - 3072 37th Annual International Conference of the IEEE-Engineering-in-Medicine-and-Biology-Society (EMBC) 3069 3072 US Milan, ITALY 2015-08-25 2015 37TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC) 000371717203087 2-s2.0-84953271728