Active Contour Segmentation using Level Set Function with Enhanced Image from Prior Intensity
- Active Contour Segmentation using Level Set Function with Enhanced Image from Prior Intensity
- 김선희; 김영준; 이득희; 박세형
- Image enhancement; Image segmentation
- Issue Date
- IEEE Engineering in Medicine and Biology Society (EMBC)
- , 1-4
- Abstract—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.
- Appears in Collections:
- KIST Publication > Conference Paper
- Files in This Item:
There are no files associated with this item.
- RIS (EndNote)
- XLS (Excel)
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.