Title :
Rotational Invariant Operators Based on Steerable Filter Banks
Author :
Shi, X. ; Castro, A. L Ribeiro ; Manduchi, R. ; Montgomery, R.
Author_Institution :
Apple Comput. Inc., Cupertino, CA
Abstract :
We introduce a technique for designing rotation invariant operators based on steerable filter banks. Steerable filters are widely used in computer vision as local descriptors for texture analysis. Rotation invariance has been shown to improve texture-based classification in certain contexts. Our approach to invariance is based on solving the partial differential equation associated with the formulation of invariance in a Lie group framework
Keywords :
Lie groups; channel bank filters; computer vision; image classification; image texture; partial differential equations; Lie group framework; computer vision; partial differential equation; rotational invariant operator; steerable filter bank; texture-based classification; Channel bank filters; Computer vision; Filter bank; Filtering; Image analysis; Image texture analysis; Kernel; Nonlinear filters; Partial differential equations; Prototypes; Channel bank filters; filtering; image orientation analysis; multidimensional signal processing;
Journal_Title :
Signal Processing Letters, IEEE
DOI :
10.1109/LSP.2006.879467
