Title :
Covariance methods in computer vision
Author :
Liu, Zhi-Qiang ; Madiraju, Sharma ; Kitchen, Les ; Dance, Sandy
Author_Institution :
Dept. of Comput. Sci., Melbourne Univ., Parkville, Vic., Australia
Abstract :
We discuss the use of covariance methods in invariant feature extraction, texture segmentation, edge detection, and surface geometry analysis. The covariance technique is used to compute local descriptors and to index roughness, anisotropy, or general textural differences. We also present a simple yet effective edge detection algorithm using a neural network which is trained by invariant features generated from covariance matrices
Keywords :
computer vision; covariance matrices; edge detection; feature extraction; image representation; image segmentation; image texture; learning (artificial intelligence); neural nets; anisotropy; computer vision; covariance matrices; covariance methods; edge detection; edge detection algorithm; feature representation method; invariant feature extraction; local descriptors; neural network; roughness; surface geometry analysis; textural differences; texture segmentation; Anisotropic magnetoresistance; Computer vision; Covariance matrix; Feature extraction; Geometry; Image edge detection; Neural networks; Rough surfaces; Surface roughness; Surface texture;
Conference_Titel :
Signal Processing, 1996., 3rd International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-2912-0
DOI :
10.1109/ICSIGP.1996.566219
