Skip to Main Content
Skip Nav Destination
ASME Press Select Proceedings
International Symposium on Information Engineering and Electronic Commerce, 3rd (IEEC 2011)
C. B. Povloviq
C. B. Povloviq
National Technical University of Ukraine
Search for other works by this author on:
C. W. Lu
C. W. Lu
Huangshi Institute of Technology
Search for other works by this author on:
No. of Pages:
ASME Press
Publication date:

In the process of image segmentation, level set model can effectively use the regional and global information, achieve the target boundary location, maintain linear smooth and easy to handle topological structure of the curve. But the selection of parameters in the model directly influences the quality and effect of segmentation. In this paper, according to the parameter selection difficulties caused slow constringency and big error problems. This paper introduce cultural algorithm to achieve image segmentation automatically, under the guidance of the situation knowledge and normative knowledge, a quasi-optimal solution can be found faster through a reasonable set of population space. The algorithm completely use the computer, eliminate the process of traditional level set model manually parameters calibration. Through the parameters of improvement of search strategy, improve the efficiency of the image segmentation. A large number of typical images results show that this method can be achieved more quickly at image segmentation.

1 Cultural Algorithms
2 Level Set Model
3 Parameters Automatically Selected
4 Experimental Results and Analysis
5 Summary
This content is only available via PDF.
You do not currently have access to this chapter.
Close Modal

or Create an Account

Close Modal
Close Modal