In this paper, a whitening-based algorithm has been applied to sparse non-negative matrix factorization (NMF) as a preprocessing practice enhancing the identification of buried object, significantly. In fact, without utilizing a suitable whitening algorithm, the input signals are very similar to one another. Therefore, conventional approaches are not able to identify and properly discriminate desired buried objects. A suitable whitening algorithm makes the covariance matrix diagonal, such that the processed signals highly resembles the unprocessed versions. Such a similarity would be helpful to identify new received signal. In this study, we have employed the zero-phase component analysis (ZCA) as our whitening method. Hence, although signals of different targets are very similar in many cases, the mentioned advantages, achieved by whitening method, make identification of targets much easier.