Joint representations have experimented a significant height in signal processing during the last decades, to such an extent that there is no topic they have not been utilized for. Within a sea of joint representations existent in the literature, one of them concerns the present work: the log-Gabor multiresolution transform. Its significant mathematical properties (low spectral overlapping, high selectivity, shift-invariance, self-invertibility, complex-valued) and similarity to the cortical area V1 of the Visual Human System allow to extract salient features which traces new routes to face...