Generalized structure tensor: Difference between revisions

Content deleted Content added
cleanup
No edit summary
Line 10:
volume = 26|
year = 2004|
}}</ref>, GST, is an extension of the Cartesian [[Structure Tensor]] to the [[Curvilinear coordinates]]. It is mainly used as a way to detect and to represent the "direction" parameters of curves, just like the Cartesian structure tensor detects and represents the direction in Cartesian coordinates. Detection of curveCurve families generated by pairs of locally orthogonal functions are best studied.
 
 
It is a widely known method in applicatons of image and video processing including computer vision. Some applications include biometric identification by fingerprints<ref name=fronthaler08tip>{{cite article|
title=Local features for enhancement and minutiae extraction in fingerprints|
author = H. Fronthaler and K. Kollreider and J. Bigun|
journal=Image Processing, IEEE Transactions on|
volume=17|
number=3|
pages=354--363|
issn=1057-7149|
year=2008|
publisher=IEEE|
}}</ref>, and studies of human tissue sections<ref name=Schmitt>{{cite article|
author=O. Schmitt, H. Birkholz|
title=Improvement in cytoarchitectonic mapping by combining electrodynamic modeling with local orientation in high-resolution images of the cerebral cortex|
journal=Microsc. Res. Tech.|
volume= 74|
year=2010|
pages= pp. 225–-243
}}</ref>,
<ref name=Schmitt2>{{cite article|
author=O. Schmitt, M. Pakura, T. Aach, L. Homke, M. Bohme, S. Bock, S. Preusse|
title=Analysis of nerve fibers and their distribution in histologic sections of the human brain|
journal=Microsc. Res. Tech.|
volume= 63|
year=2004|
pages= pp. 220–243|
}}</ref>.
 
 
Let the term image represent a function