Texture representations using subspace embeddings

• We propose a framework to map local texture patches into a low-dimensional texture subspace.
• The proposed subspace texture representations have strong resistance to image deformations.
• The proposed subspace texture representations are more distinctive and more compact than traditional representations.
• We investigate both linear and non-linear subspace embedding methods including PCA, LDA, and LPP.
• The proposed framework is evaluated on two benchmark datasets and achieves the state-of-the-art results.

In this paper, we propose a texture representation framework to map local texture patches into a low-dimensional texture subspace. In natural texture images, textons are entangled with multiple factors, such as rotation, scaling, viewpoint variation, illumination change, and non-rigid surface deformation. Mapping local texture patches into a low-dimensional subspace can alleviate or eliminate these undesired variation factors resulting from both geometric and photometric transformations. We observe that texture representations based on subspace embeddings have strong resistance to image deformations, meanwhile, are more distinctive and more compact than traditional representations. We investigate both linear and non-linear embedding methods including Principle Component Analysis (PCA), Linear Discriminant Analysis (LDA), and Locality Preserving Projections (LPP) to compute the essential texture subspace. The experiments in the context of texture classification on benchmark datasets demonstrate that the proposed subspace embedding representations achieve the state-of-the-art results while with much fewer feature dimensions.