Notice bibliographique
- Notice
000 02511n0 m 22000271 45as
001 FRBNF446812390000007
008 170801s 2016 cheng b 001
009 a
009 sa s 1 a c
017 .. $o OCoLC $a 960852023 $k ZWZ $l fre $m OCLCO $n ncafnor
020 .. $a 9783319414713
051 .. $a txt $b c
245 1. $a Local features in natural images via singularity theory $d Texte électronique $f James Damon, Peter Giblin, Gareth Haslinger
260 .. $a Cham $c Springer International Publishing $d 2016, cop. 2016
280 .. $a 1 online resource
295 1. $a Lecture Notes in Mathematics $v 2165
300 .. $a Titre provenant de l'écran-titre
300 .. $a Reproduction numérique de l'édition de Cham : Springer, 2016
300 .. $a La pagination de l'édition imprimée est de X-255 pages
306 .. $a Fichier PDF.
306 .. $a Fichier EPUB.
330 .. $a This monograph considers a basic problem in the computer analysis of natural images,
which are images of scenes involving multiple objects that are obtained by a camera
lens or a viewer's eye. The goal is to detect geometric features of objects in the
image and to separate regions of the objects with distinct visual properties. When
the scene is illuminated by a single principal light source, we further include the
visual clues resulting from the interaction of the geometric features of objects,
the shade/shadow regions on the objects, and the "apparent contours". We do so by
a mathematical analysis using a repertoire of methods in singularity theory. This
is applied for generic light directions of both the "stable configurations" for these
interactions, whose features remain unchanged under small viewer movement, and the
generic changes which occur under changes of view directions. These may then be used
to differentiate between objects and determine their shapes and positions