LAUSR

Hyperspectral images possess the characteristics of high dimensionality, which causes “dimensional disaster” and low classification accuracy. In order to solve the problems, based on traditional k-means algorithm, considering the importance of different bands for classification, and also combining both intra-class and inter-class information, a Kmeans-CM (K-means with correlation coefficient and maximize inter-class distance) algorithm with spectral angle mapper for hyperspectral image classification is proposed. First, we define weights of bands by introducing coefficient of variation and spectral angle mapping, which measures the importance of bands for classification, so as to make up for the deficiency of the traditional K-means algorithm to treat each band equally. Second, we introduce correlation coefficient to reset the intra-class distances in order to intensify correlation between pixels in the same category. Then, in order to reduce effect of local optimum of clustering effect, we introduce inter-class information for clustering by maximizing the distance between class centers and global center. Finally, the K-means clustering objective function is redefined according to the band weights and intra-class, inter-class information, and also solving optimally. The overall classification accuracy of the method reached 84.47%, 90.08% and 80.45% on classical hyperspectral data sets Pavia University, Salinas and Botswana respectively. And comparing with the traditional K-means algorithm, the CV-K-means algorithm and the CK-means algorithm, the experimental results show that the proposed algorithm can effectively improve classification accuracy of hyperspectral images, thus proving that the algorithm has good classification performance.