Harmonic Analysis for Hyperspectral Image Classification Integrated With PSO Optimized SVM

A novel hyperspectral image classification approach named as HA-PSO-SVM is proposed by integrating the harmonic analysis (HA), particle swarm optimization (PSO), and support vector machine (SVM). In the combined method, HA is first proposed to transform the pixels from spectral domain into frequency domain expressed by amplitude, phase and residual, yielding more functional and discriminative features for classification purpose. In this step, the original pixel vector can also be reconstructed. Then, PSO is adapted to optimize the penalty parameter C and the kernel parameter gamma for SVM, which leads to improved classification performance. Finally, the extracted features are classified with the optimized model. The experimental results with three hyperspectral data sets collected by the airborne visible infrared imaging spectrometer (AVIRIS) and the reflective optics spectrographic imaging system (ROSIS) indicate that the proposed method provides improved classification performance compared with some related techniques in terms of both the classification accuracy and the computational time.