A neural network method of selective end-member for pixel unmixing

Abstract

Remote sensing images contain a lot of mixed image pixels, but it is difficult to classify these pixels. If the number of pixel's end-member is regarded as unchangeable, the traditional pixel unmixing algorithm cannot get a good result. In this paper we develop a new method of selective end-members for pixel unmixing based on the fuzzy ARTMAP neural network, which firstly compares the pixel's spectral to the conference one and then gets the number of end-member. When it is taken into account, we use an ARTMAP neural network to extract subpixel information. Finally, experimental results show that the selective end-member algorithm achieves improvement over conventional ANN algorithms and conventional linear algorithms.