A fuzzy local neighbourhood-attraction-based information c-means clustering algorithm for very high spatial resolution imagery classification

This letter presents a fuzzy local neighbourhood-attraction-based information c-means clustering (FLNAICM) approach to classify very high spatial resolution imagery (HSRI). In which local spatial and grey information based on the neighbourhood attractions between the centre pixel and its neighbouring pixels is incorporated to enhance the insensitivity to noise of the conventional fuzzy c-means (FCM) algorithm and preserve image details. The main contributions of FLNAICM are first, neighbourhood attractions are used as a measure to balance the effects of neighbourhood pixels on the centre pixel. As a result, appropriate local spatial and grey information is incorporated to improve the robustness and noise insensitiveness of the conventional FCM. Second, FLNAICM is fully free of any parameters selection. Two different remotely sensed images are used in experiments to test the performance of FLNAICM. Experimental results indicate that FLNAICM achieves high accuracy and hence provides an effective classification method for HSRI.

[1]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[2]  Daoqiang Zhang,et al.  Robust image segmentation using FCM with spatial constraints based on new kernel-induced distance measure , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[3]  Maoguo Gong,et al.  Change Detection in Synthetic Aperture Radar Images based on Image Fusion and Fuzzy Clustering , 2012, IEEE Transactions on Image Processing.

[4]  J. C. Dunn,et al.  A Fuzzy Relative of the ISODATA Process and Its Use in Detecting Compact Well-Separated Clusters , 1973 .

[5]  Xi Chen,et al.  A Spatial Clustering Method With Edge Weighting for Image Segmentation , 2013, IEEE Geoscience and Remote Sensing Letters.

[6]  James C. Bezdek,et al.  Pattern Recognition with Fuzzy Objective Function Algorithms , 1981, Advanced Applications in Pattern Recognition.

[7]  R. G. Oderwald,et al.  Assessing Landsat classification accuracy using discrete multivariate analysis statistical techniques. , 1983 .

[8]  G. Foody.  Thematic map comparison: Evaluating the statistical significance of differences in classification accuracy , 2004 .

[9]  Stelios Krinidis,et al.  A Robust Fuzzy Local Information C-Means Clustering Algorithm , 2010, IEEE Transactions on Image Processing.

[10]  D M Clarke,et al.  Comparing correlated kappas by resampling: is one level of agreement significantly different from another? , 1996, Journal of psychiatric research.

[11]  Aly A. Farag,et al.  A modified fuzzy c-means algorithm for bias field estimation and segmentation of MRI data , 2002, IEEE Transactions on Medical Imaging.

[12]  Dan Hu,et al.  Land cover classification of remote sensing imagery based on interval-valued data fuzzy c-means algorithm , 2014, Science China Earth Sciences.

[13]  Wenzhong Shi,et al.  Unsupervised classification based on fuzzy c-means with uncertainty analysis , 2013 .

[14]  Antonio J. Plaza,et al.  A Quantitative and Comparative Assessment of Unmixing-Based Feature Extraction Techniques for Hyperspectral Image Classification , 2012, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[15]  Daoqiang Zhang,et al.  Fast and robust fuzzy c-means clustering algorithms incorporating local information for image segmentation , 2007, Pattern Recognit..