Title :
An improved FCM for image segmentation
Author :
Liping, Cao ; Zhihua, Xia
Author_Institution :
Dept. of Electr. & Mech. Eng., Baoding Vocational & Tech. Coll., Baoding, China
Abstract :
A novel image segmentation method based on modified fuzzy c-means (FCM) is proposed in this paper. Using the neighborhood pixels selectively, a spatial constraint punishment term is added in the objective function of standard FCM to improve the robust to noise, raise the convergent rate and reduce computing time. Experiments on standard image segmentation prove the availability of the improvement.
Keywords :
image segmentation; fuzzy c-means; image segmentation; spatial constraint punishment term; Clustering algorithms; Convergence; Educational institutions; Image segmentation; Mechanical engineering; Noise; Robustness; fuzzy c-means; image segmentation; object function; spatial constraint;
Conference_Titel :
Electric Information and Control Engineering (ICEICE), 2011 International Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-8036-4
DOI :
10.1109/ICEICE.2011.5777510
