Learning rotation invariant convolutional filters for texture classification

We present a method for learning discriminative steerable filters using a shallow Convolutional Neural Network (CNN). We encode rotation invariance directly in the model by tying the weights of groups of filters to several rotated versions of the canonical filter in the group. These filters can be used to extract rotation invariant features well-suited for image classification. We test this learning procedure on a texture classification benchmark, where the orientations of the training images differ from those of the test images. We obtain results comparable to or better than the state-of-the-art. Besides numerical advantages, our proposed rotation invariant CNN decreases the number of parameters to be learned, thus showing more robustness in small training set scenarios than a standard CNN.