A sparse texture representation using local affine regions

Svetlana Lazebnik (1) , Cordelia Schmid (2) , Jean Ponce (1)

1 The Beckman Institute for Advanced Science and Technology
2 LEAR - Learning and recognition in vision

This paper introduces a texture representation suitable for recognizing images of textured surfaces under a wide range of transformations, including viewpoint changes and nonrigid deformations. At the feature extraction stage, a sparse set of affine Harris and Laplacian regions is found in the image. Each of these regions can be thought of as a texture element having a characteristic elliptic shape and a distinctive appearance pattern. This pattern is captured in an affine-invariant fashion via a process of shape normalization followed by the computation of two novel descriptors, the spin image and the RIFT descriptor. When affine invariance is not required, the original elliptical shape serves as an additional discriminative feature for texture recognition. The proposed approach is evaluated in retrieval and classification tasks using the entire Brodatz database and a publicly available collection of 1,000 photographs of textured surfaces taken from different viewpoints.

Mots clés: Index Terms- Image processing and computer vision; feature measurement; pattern recognition; texture

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Svetlana Lazebnik, Cordelia Schmid, Jean Ponce. A sparse texture representation using local affine regions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27 (8), pp.1265--1278. ⟨10.1109/TPAMI.2005.151⟩. ⟨inria-00548530⟩