Hyperspectral image classification using wavelet packet analysis and gray prediction model

The main focus of hyperspectral image classification is the ability to extract information from a pixel´s hyperspectral curve. In this paper, we propose a new classification method based on wavelet packet analysis and gray prediction model of hyperspectral reflectance curves. The wavelet packet analysis is used for feature extraction, while the gray prediction model is applied for dimensionality reduction. The efficiency of the proposed method will be estimated by the multivariate statistical analysis (i.e. Mahalanobis distance and quantile). Experimental results indicate that our algorithm has a relatively high efficiency, and classification accuracy of 99.3%.