The invention provides a hyperspectral image characteristic parallel extraction and classification method. By adopting three-dimensional spatial domain and frequency domain combination analysis, parallel characteristic extraction of three-dimensional and hyperspectral images is carried out, and then the characteristics are enhanced and integrated, and in addition, influences of noises on accuracy are greatly reduced by fully using rich information of high-dimensional data and a structural relationship between the characteristics. Various phases, directions, frequency domains, and three-dimensional space coding methods are deeply researched, and by starting from structural relationships between directions and frequencies of various Gabor characteristics, changing characteristics of signals of a spatial-spectral domain and the frequency domain are extracted in a combined way, and at the same time, an intelligent algorithm is innovatively introduced in waveband selection, and therefore under a precondition of guaranteeing identification accuracy, redundant information is reduced, identification efficiency is improved, and a wide application and popularization prospect is provided.