A modified iterative N-FINDR algorithm is developed for fully automatic extraction of endmembers from hyperspectral image data. This algorithm exploits the advantages of iterative NFINDR technique and Iterative Error analysis technique. The experiments using a simulated hyperspectral image data shows that the optimum number of endmembers can be automatically decided. The extracted endmembers and finally generated abundance fraction maps show the potentialities of the proposed algorithm. More studies are needed for verification of the applicability of the algorithm to the real hyperspectral image data where the absence of pure pixels is common.