1 1 Ï
2015 c 1
uÀÆÆ(g,Æ)
Journal of East China Normal University (Natural Science)
No. 1
Jan. 2015
©©©ÙÙÙ???ÒÒÒ: 1000-5641(2015)01-0161-11
«««UUU???YYY²²²888ÌÌÌÄÄÄÓÓÓ+++...
Ç á, Á ¯
(uÀÆ O¥%, þ° 200062)
Á: ÏLÚOäkãOrUåÛÜ«&E, JÑ«U?Y²8ÌÄÓ+
.. (ÜKؼêÚäkãØA:Ý8+g, ½Â«#ÎÒØå¼
ê(SPF), d¼êUéÐ?nÝØþ!! é>.ز(¯K. ¿, Ú\¨v, (
Y²8¼ê·A5. ý¢ãÚܤã¢(JL², T.Âñ×, äk|D5, é
©8Iã¯a, U?nf>.õ8Iã.
'c: «U?Y²8ÌÄÓ+.; f>.; ÝØþ!; ã©
¥ã©aÒ: O948 ©zI£è: A
DOI: 10.3969/j.issn.1000-5641.2015.01.020
An improved active contour model based on level set method
WU Zhang, ZHU Min
(Computing Center, East China Normal University, Shanghai 200062, China)
Abstract: By using the local regional information which has the ability to enhance
the image, an improved active contour model based on level set method is proposed.
Defining a novel SPF function with a nonnegative kernel function and local intensity
clustering property, the novel model could draw upon intensity information in local regions
at a controllable scale. In addition, the penalizing term which can be called distance
regularization term drives the motion of the zero level set toward desired locations.
Experimental results for real and synthetic images sh ow the desirable proposed method
performances and the model efficiency on intensity inhomogeneities and weak boundaries.
Key words: an improved active contour model based on level set method; weak
boundary; int ensity inhomogeneity; image segmentation
0 Ú ó
3ã©¥2A^¹ÄÓ+.(¡.)
[1]
äkK©! >u
ÿ! «)²;ã©{A:. ÙÄg: ÏL5gÓ+gSÜUþÚ
ÂvFÏ: 2014-04
Ä78: I[863OyÜ1EB?;XÚï(2013AA01A211)
1ö: Çá, å, a¬ïÄ), ïÄã?nª£O. E-mail: naruto wu@126.com.
Ï&ö: Á¯, å, p?ó§, a¬), ïÄã?nª£O.
E-mail: mzhu@cc.ecnu.edu.cn.
