In this paper we propose a feature selection method that uses the mutual information (MI) measure on a Principal Component Analysis (PCA) based decomposition. PCA nds a linear projection of the data in a non-supervised way, which preserves the larger variance components of the data under the reconstruction error criterion. Previous works suggest that using the MI among the PCA projected data and the class labels applied to feature selection can add the missing discriminability criterion to the optimal reconstruction feature set. Our proposal goes one step further, de ning a global framework to add independent selection criteria in order to lter misleading PCA components while the optimal variables for classi cation are preserved. We apply this approach to a face recognition problem using the AR Face data set. Notice that, in this problem, PCA projection vectors strongly related to illumination changes and occlusions are usually preserved given theirhigh variance. Our additional selection tasks are able to discard this type of features while the relevant features to perform the subject recognition classi cation are kept. The experiments performed show an improved feature selection process using our combined criterion.