A sparse texture representation using local affine regions

Citations Over TimeTop 1% of 2005 papers

Abstract

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 servee 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.

Related Papers

• → A performance study of image segmentation techniques(2015)53 cited
• → An Affine Symmetric Image Model and Its Applications(2010)4 cited
• → A review paper on image segmentation techniques based on colour and texture features(2023)1 cited
• → A Study Of Texture Segmentation(1986)
• → Comprehensive study of Multi heuristic image segmentation techniques(2019)