- Endmember extraction (EE) is an important step in hyperspectral data unmixing. There are many algorithms for Endmember extraction, one of the most common methods is the N-FINDR. The N-FINDR is the base for numerous EE algorithms including the Successive N-FINDR (SC N-FINDR) and the Random N-FINDR (RSC N-FINDR). The main issues of N-FINDR based algorithms is the enormous computation time, inconsistent final endmember selection and the fact that the amount of Endmembers is chosen in advance. This choice is made without knowing the amount of true Endmembers in the hyperspectral data. In this paper, a single run of the k-means++ algorithm is suggested in order to automate the process. The solution of the immense computation time problem consists in the use orthogonal projection of the found Endmember on the rest of the pixels, and using SAM method in order to eliminate similar pixels from the image.