A Novel Method for Hyperspectral Image Classification Based on Laplacian Eigenmap Pixels Distribution-Flow

The accurate classification of hyperspectral images is an important task for many practical applications. In this paper, a new method for hyperspectral image classification is proposed based on manifold learning algorithm, The approach introduced here presents three major contributions: 1) a new Laplacian eigenmap pixels distribution-flow (LE PD-Flow) is proposed for hyperspectral image analysis, in which, a new joint spatial-pixel characteristics distance (JSPCD) measure is constructed to improve the accuracy of classification and a suitable weighting factor is used to distinguish data points of different classes by combining the spectral feature with the spatial feature; 2) the adjustment strategy of each manifold mappings is addressed, which allows not only better visualization of the results, but also the comparisons of mapping results with an appropriate measurement; 3) in order to get useful boundary points used for classification, single threshold and multiple thresholds method are presented to solve small scale and large scale classification problem, respectively. We can easily obtain the expected classification results by adjusting the weights of the two kinds of feature of hyperspectral image. With the LE PD-Flow, variation of pixels on the boundaries for classification can be found, and then hyperspectral data can be labeled with high accuracy. Experimental results show that the proposed method is effective for classification of hyperspectral image.