Abstract: To solve the problem of large solution space and a mass of local minima in the traditional non-negative matrix factorization (NMF), a volume and sparseness constrained NMF (VSC-NMF) algorithm was proposed. Firstly, end-members extracted by vertex component analysis (VCA) in hyperspectral image were taken as initialization of end-member matrix so as to accelerate the convergence speed. Then, the traditional NMF was extended by incorporating the minimum volume constraint and abundance's sparseness constraint to achieve better separation of mixed pixels. The experimental results on synthetic and real data illustrate that the proposed algorithm can overcome the shortcomings of traditional NMF and obtain more accurate end-members and corresponding abundance, especially in sparser hyperspectral image.