DocumentCode :
557750
Title :
The research on segmentation of complex object
Author :
Wang, Xiaofei ; Pang, Quan
Author_Institution :
Inst. of Biol. Eng. & Instrum., Hang Zhou Dianzi Univ., Hangzhou, China
Volume :
3
fYear :
2011
fDate :
15-17 Oct. 2011
Firstpage :
1277
Lastpage :
1281
Abstract :
It is difficult to use the traditional image segmentation method to segment the complex object whose boundary is blurred from the background. The active contour model, based on level set, is widely used in recent years and selected to segment this type of object in this paper. To increase the speed of segmentation, the fast active contour model without need to solve partial differential equation is used in this paper. This paper proposes a new way of thinking about designing the data-dependent speed function in the fast active model and gives the corresponding general speed function. The probability estimate theory and the conventional CV model are introduced into the data-dependent speed function, and then this paper proposes two novel fast models which can be called histogram-based fast model and CV-based fast model. The two models are studied both theoretically and experimentally. Finally a conclusion can be drawn that the histogram-based fast model is applied to segment the complex object from the background.
Keywords :
edge detection; image segmentation; partial differential equations; probability; CV-based fast model; active contour; blurred background; complex object segmentation; data-dependent speed function; histogram-based fast model; level set; partial differential equation; probability estimate theory; Active contours; Biological system modeling; Computational modeling; Estimation; Image segmentation; Mathematical model; Switches; CV model; blurred boundary; complex object; fast active contour model; probability estimate;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image and Signal Processing (CISP), 2011 4th International Congress on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-9304-3
Type :
conf
DOI :
10.1109/CISP.2011.6100429
Filename :
6100429
Link To Document :
بازگشت