We develop a new approach for texture classification independent of affine transforms. Based on a spectral representation of texture images under affine transform, anisotropic scale invariant signatures of the orientation spectrum distribution are extracted. A peaks distribution vector (PDV) obtained on the distribution of these signatures captures texture properties invariant to affine distortion. The PDV is used to measure the similarity between textures. Experimental results show the efficiency of the PDV for affine invariant texture classification