Open AccessAdaptive fuzzy c‐means algorithm based on local noise detecting for image segmentation
Author(s) -
Guo FangFang,
Wang XiuXiu,
Shen Jie
Publication year - 2016
Publication title -
iet image processing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.401
H-Index - 45
eISSN - 1751-9667
pISSN - 1751-9659
DOI - 10.1049/iet-ipr.2015.0236
Subject(s) - image segmentation , robustness (evolution) , computer science , artificial intelligence , noise (video) , algorithm , segmentation , pattern recognition (psychology) , image (mathematics) , fuzzy logic , segmentation based object categorization , image noise , scale space segmentation , computer vision , mathematics , biochemistry , chemistry , gene
Adding spatial penalty terms in fuzzy c‐means (FCM) models is an important approach for reducing the noise effects in the process of image segmentation. Though these algorithms have improved the robustness to noises in a certain extent, they still have some shortcomings. First, they are usually very sensitive to the parameters which are supposed to be tuned according to noise intensities. Second, in the case of inhomogeneous noises, using a constant parameter for different image regions is obviously unreasonable and usually leads to an unideal segmentation result. For overcoming these drawbacks, a noise detecting‐based adaptive FCM for image segmentation is proposed in this study. Two image filtering methods, playing the roles of denoising and maintaining detail information are utilised in the new algorithm. The parameters for balancing these two parts are computed by measuring the variance of grey‐level values in each neighbourhood. Numerical experiments on both synthetic and real‐world image data show that the new algorithm is effective and efficient.