TY - JOUR
T1 - A fuzzy clustering algorithm with spatial robust estimation constraint for noisy color image segmentation
AU - Mújica-Vargas, Dante
AU - Gallegos-Funes, Francisco J.
AU - Rosales-Silva, Alberto J.
N1 - Funding Information:
This work is supported by National Polytechnic Institute of Mexico and National Council on Science and Technology of Mexico (Conacyt).
PY - 2013/3/1
Y1 - 2013/3/1
N2 - In this paper, we introduce two enhanced Fuzzy C-Means (FCM) clustering algorithms with spatial constraints for noisy color image segmentation. The Rank M-type L (RM-L) and L-estimators are used to obtain the sufficiently spatial information of the pixels. These estimators are involved into the FCM algorithm to provide robustness for the proposed segmentation schemes. The performance of the proposed algorithms is tested in real images under different noise conditions by simulating salt and pepper, Gaussian, and speckle noises, as well as with two mixtures of them. Simulation results indicate that the proposed methods consistently outperform other color image segmentation algorithms used as comparative. Additionally, the proposed algorithms are tested for segmenting a remote sensing image, where the noise is not known beforehand implied. Finally, the proposed algorithms have the robustness and effectiveness needed for image segmentation in the presence and absence of noise.
AB - In this paper, we introduce two enhanced Fuzzy C-Means (FCM) clustering algorithms with spatial constraints for noisy color image segmentation. The Rank M-type L (RM-L) and L-estimators are used to obtain the sufficiently spatial information of the pixels. These estimators are involved into the FCM algorithm to provide robustness for the proposed segmentation schemes. The performance of the proposed algorithms is tested in real images under different noise conditions by simulating salt and pepper, Gaussian, and speckle noises, as well as with two mixtures of them. Simulation results indicate that the proposed methods consistently outperform other color image segmentation algorithms used as comparative. Additionally, the proposed algorithms are tested for segmenting a remote sensing image, where the noise is not known beforehand implied. Finally, the proposed algorithms have the robustness and effectiveness needed for image segmentation in the presence and absence of noise.
KW - Color images
KW - Fuzzy C-Means
KW - L-estimator
KW - Noise
KW - RM-L-estimator
KW - Segmentation
UR - http://www.scopus.com/inward/record.url?scp=84881152060&partnerID=8YFLogxK
U2 - 10.1016/j.patrec.2012.10.004
DO - 10.1016/j.patrec.2012.10.004
M3 - Artículo
SN - 0167-8655
VL - 34
SP - 400
EP - 413
JO - Pattern Recognition Letters
JF - Pattern Recognition Letters
IS - 4
ER -