Title :
Feature Detection from the Maximal Response to a Spherical Quadrature Filter Set
Author :
Marchant, Roman ; Jackway, Paul
Abstract :
In this paper we describe a novel method of feature detection and classification using the maximal response of a set of spherical quadrature filters to either a line-segment or wedge-segment signal type. This is achieved via a rotation and illumination invariant distance function. The development of the method is described, and some experimental results are provided to demonstrate the usefulness of the technique.
Keywords :
feature extraction; filtering theory; image classification; lighting; feature classification; feature detection; illumination invariant distance function; line-segment signal type; maximal response; rotation invariant distance function; spherical quadrature filter set; wedge-segment signal type; Band pass filters; Estimation; Feature extraction; Image edge detection; Kernel; Transforms; Vectors;
Conference_Titel :
Digital Image Computing Techniques and Applications (DICTA), 2012 International Conference on
Conference_Location :
Fremantle, WA
Print_ISBN :
978-1-4673-2180-8
Electronic_ISBN :
978-1-4673-2179-2
DOI :
10.1109/DICTA.2012.6411715
