In this paper, a new robust principal component analysis (RPCA) method is proposed which enables us to exploit the main components of a given corrupted data with non-Gaussian outliers. The proposed method is based on the alpha-divergence which is a parametric measure from information geometry. The proposed method which is adjustable by the hyperparameter alpha, reduces to the classical PCA under certain parameters. In order to derive the main components, the alpha-divergence between the empirical data distribution and the assumed model is minimized with respect to the unknown parameters and then the singular value decomposition (SVD) of the estimated covariance matrix exploits the main direction of data. The proposed method is applied to some video and signal processing applications and the results show the superiority of the method over the classical PCA and other existing robust methods.