Segmentation-Based Projected Clustering of Hyperspectral Images Using Mutual Nearest Neighbour

In this study, a simple yet effective projected clustering method is proposed for hyperspectral images. The proposed method assimilates segmentation, clustering, and local band selection within its framework. Initially, a segmented map of the hyperspectral image is obtained by using <inline-formula><tex-math notation="LaTeX">$k$</tex-math> </inline-formula>–means algorithm. In the subsequent stage, the obtained segments are considered as clusters and are merged by utilizing the mutual nearest neighbour information. In the last stage, the method identifies the <inline-formula><tex-math notation="LaTeX">$k$</tex-math></inline-formula> significant clusters using a criterion based on entropy. The final cluster map is obtained by assigning all the remaining clusters to these <inline-formula> <tex-math notation="LaTeX">$k$</tex-math></inline-formula> significant clusters. Additionally, the clustering stages make use of multiple subspaces, obtained by deploying a local band selection approach. To test the performance of the proposed method, experiments are conducted over five hyperspectral images and is further compared with other clustering frameworks. The efficacy of the proposed method is confirmed by the experiments conducted over these images.

[1]  Russell G. Congalton,et al.  Assessing the accuracy of remotely sensed data : principles and practices , 1998 .

[2]  O. Dikshit,et al.  Projected clustering of hyperspectral imagery using region merging , 2016 .

[3]  Chris H. Q. Ding,et al.  K-nearest-neighbor consistency in data clustering: incorporating local information into global optimization , 2004, SAC '04.

[4]  Maurice Borgeaud,et al.  Kernel Low-Rank and Sparse Graph for Unsupervised and Semi-Supervised Classification of Hyperspectral Images , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[5]  Philip S. Yu,et al.  Fast algorithms for projected clustering , 1999, SIGMOD '99.

[6]  Farid Melgani,et al.  Clustering of Hyperspectral Images Based on Multiobjective Particle Swarm Optimization , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[7]  Saeid Homayouni,et al.  An Improved FCM Algorithm Based on the SVDD for Unsupervised Hyperspectral Data Classification , 2013, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[8]  Hans-Peter Kriegel,et al.  Clustering high-dimensional data: A survey on subspace clustering, pattern-based clustering, and correlation clustering , 2009, TKDD.

[9]  Sean Hughes,et al.  Clustering by Fast Search and Find of Density Peaks , 2016 .

[10]  G. Krishna,et al.  Agglomerative clustering using the concept of mutual nearest neighbourhood , 1978, Pattern Recognit..

[11]  Jiawei Han,et al.  Document clustering using locality preserving indexing , 2005, IEEE Transactions on Knowledge and Data Engineering.

[12]  Claude Cariou,et al.  Unsupervised Nearest Neighbors Clustering With Application to Hyperspectral Images , 2015, IEEE Journal of Selected Topics in Signal Processing.

[13]  T. Caliński,et al.  A dendrite method for cluster analysis , 1974 .

[14]  C. A. Murthy,et al.  Unsupervised Feature Selection Using Feature Similarity , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[16]  Andrew Y. Ng,et al.  Learning Feature Representations with K-Means , 2012, Neural Networks: Tricks of the Trade.

[17]  Philip S. Yu,et al.  Finding generalized projected clusters in high dimensional spaces , 2000, SIGMOD '00.

[18]  Nicolas Gillis,et al.  Hierarchical Clustering of Hyperspectral Images Using Rank-Two Nonnegative Matrix Factorization , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[19]  Liangpei Zhang,et al.  Spectral–Spatial Sparse Subspace Clustering for Hyperspectral Remote Sensing Images , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[20]  O. Dikshit,et al.  Comparative study on projected clustering methods for hyperspectral imagery classification , 2016 .

[21]  Onkar Dikshit,et al.  Segmentation-based clustering of hyperspectral images using local band selection , 2017 .

[22]  P. Rousseeuw.  Silhouettes: a graphical aid to the interpretation and validation of cluster analysis , 1987 .