Title :
Image Segmentation Using FCM Optimized by Quantum Immune Clone Algorithm
Author :
Yu Li ; Fei Tong ; Guojian Cheng
Author_Institution :
Coll. of Comput. Sci., Xi´an Shiyou Univ., Xi´an, China
Abstract :
The traditional Fuzzy C-Means (FCM) clustering algorithm is usually based on the image intensity, so the segmentation results are unsatisfactory when the images are impacted by noise. Considering this shortcoming, in this paper the FCM objective function is improved by adding two kinds of spatial information: the relative position information and the intensity information of the neighborhood. Moreover, Quantum Immune Clone algorithm (QICA) is used to optimize the spatial impact factors in the objective function. The proposed algorithm has been tested in synthetic and real synthetic aperture radar (SAR) images segmentation. Experimental results demonstrate that the proposed algorithm is feasible and effective, and it can lead to higher accuracy.
Keywords :
artificial immune systems; fuzzy set theory; image segmentation; pattern clustering; FCM clustering algorithm; FCM objective function; QICA; SAR image; fuzzy c-means; image intensity; image noise; image segmentation; intensity information; quantum immune clone algorithm; relative position information; spatial information; synthetic aperture radar image; Clustering algorithms; Earthquakes; Image segmentation; Linear programming; Noise; Optimization; Signal processing algorithms; FCM clustering algorithm; Quantum Immune Clone algorithm (QICA); image segmentation; spatial information;
Conference_Titel :
Intelligent Systems Design and Engineering Applications (ISDEA), 2014 Fifth International Conference on
Conference_Location :
Hunan
Print_ISBN :
978-1-4799-4262-6
DOI :
10.1109/ISDEA.2014.127
