Skip to Main Content
Hyperspectral remote sensing image processing has become a fast growing technique in the field of remote sensing. One of the most important hyperspectral remote sensing image processing is spectral unmixing that is to decompose a mixed pixel into a collection of endmembers their corresponding abundance fractions. N-FINDR is one of the most classical and commonly used endmember extraction algorithms. However, it is a time-consuming task, even in the parallel version. This paper considers a new parallel N-FINDR algorithm, called iterative cascade parallel N-FINDR algorithm, which improves the performance of parallel N-FINDR. In experiment, our proposed algorithm demonstrates high performance for endmember extraction.