Texture classification from random features

This paper presents a simple, novel, yet very powerful approach for texture classification based on compressed sensing, suitable for large texture database applications. At the feature extraction stage, a small set of random features is extracted from local image patches. The random features are embedded into a bag of words model to perform texture classification, thus learning and classification are carried out in the compressed sensing domain. The proposed unconventional random feature extraction is simple, yet by leveraging the sparse nature of texture images, our approach outperforms traditional feature extraction methods which involve careful design and complex steps. We have conducted extensive experiments on both the CUReT and the Brodatz databases, comparing the proposed approach to three state-of-the-art texture classification methods: Patch, MR8, and LBP. We show that our approach leads to significant improvements in classification accuracy and reductions in feature dimensionality.