仿射变换
人工智能
判别式
模式识别(心理学)
图像纹理
计算机科学
特征提取
计算机视觉
不变(物理)
数学
图像分割
分割
几何学
数学物理
作者
Svetlana Lazebnik,Cordelia Schmid,Jean Ponce
标识
DOI:10.1109/tpami.2005.151
摘要
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI