Sök i LIBRIS databas



Sökning: onr:t2npcrm8r2mt5718 > Principles for Auto...

Principles for Automatic Scale Selection [Elektronisk resurs]

Lindeberg, Tony, 1964- (författare)
KTH Skolan för datavetenskap och kommunikation (CSC) (utgivare)
Publicerad: Academic Press, 1999
Ingår i: Handbook on Computer Vision and Applications. ; 239-274
Läs hela texten
Läs hela texten
Läs hela texten
  • E-artikel/E-kapitel
Sammanfattning Ämnesord
  • An inherent property of objects in the world is that they only exist as meaningful entities over certain ranges of scale. If one aims at describing the structure of unknown real-world signals, then a multi-scale representation of data is of crucial importance. Whereas conventional scale-space theory provides a well-founded framework for dealing with image structures at different scales, this theory does not directly address the problem of how to select appropriate scales for further analysis. This article outlines a systematic methodology of how mechanisms for automatic scale selection can be formulated in the problem domains of feature detection and image matching (flow estimation), respectively. For feature detectors expressed in terms of Gaussian derivatives, hypotheses about interesting scale levels can be generated from scales at which normalized measures of feature strength assume local maxima with respect to scale. It is shown how the notion of $\gamma$-normalized derivatives arises by necessity given the requirement that the scale selection mechanism should commute with rescalings of the image pattern. Specifically, it is worked out in detail how feature detection algorithms with automatic scale selection can be formulated for the problems of edge detection, blob detection, junction detection, ridge detection and frequency estimation. A general property of this scheme is that the selected scale levels reflect the size of the image structures. When estimating image deformations, such as in image matching and optic flow computations, scale levels with associated deformation estimates can be selected from the scales at which normalized measures of uncertainty assume local minima with respect to scales. It is shown how an integrated scale selection and flow estimation algorithm has the qualitative properties of leading to the selection of coarser scales for larger size image structures and increasing noise level, whereas it leads to the selection of finer scales in the neighbourhood of flow field discontinuities. 


Natural Sciences  (hsv)
Computer and Information Sciences  (hsv)
Computer Sciences  (hsv)
Naturvetenskap  (hsv)
Data- och informationsvetenskap  (hsv)
Datavetenskap (datalogi)  (hsv)
Natural Sciences  (hsv)
Computer and Information Sciences  (hsv)
Computer Vision and Robotics (Autonomous Systems)  (hsv)
Naturvetenskap  (hsv)
Data- och informationsvetenskap  (hsv)
Datorseende och robotik (autonoma system)  (hsv)

Indexterm och SAB-rubrik

scale selection
normalized derivative
feature detection
blob detection
corner detection
frequency estimation
Gaussian derivative
multi-scale representation
computer vision
Inställningar Hjälp

Beståndsinformation saknas

Fel i posten?
Teknik och format
Sök utifrån
LIBRIS söktjänster

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

Copyright © LIBRIS - Nationella bibliotekssystem

pil uppåt Stäng

Kopiera och spara länken för att återkomma till aktuell vy