Logo des Repositoriums
 

Texture-based Surface Segmentation Using Second-order Statistics of Illumination Series

dc.contributor.authorLindner, Christoph
dc.contributor.authorSchäffler, Fabian
dc.contributor.authorPuente León, Fernando
dc.contributor.editorKoschke, Rainer
dc.contributor.editorHerzog, Otthein
dc.contributor.editorRödiger, Karl-Heinz
dc.contributor.editorRonthaler, Marc
dc.date.accessioned2019-05-15T09:15:29Z
dc.date.available2019-05-15T09:15:29Z
dc.date.issued2007
dc.description.abstractMany automated visual inspection applications rely on a segmentation of surfaces into meaningful regions, for instance into defective and non-defective areas. This paper presents a segmentation approach based on illumination series, by which we denote a set of images taken under variable directional illumination. We show that co-occurrence matrices calculated from the series of images enable the extraction of suitable features for a texture-based segmentation of the surface. Depending on the selected displacement vector, the co-occurrence matrices computed within a neighbor- hood contain information about spatial variations of the surface or about the average reflection properties. The method is developed on synthetic images and is then demon- strated with cutting inserts to segment areas featuring abrasion.en
dc.identifier.isbn978-3-88579-206-1
dc.identifier.pissn1617-5468
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/22596
dc.language.isoen
dc.publisherGesellschaft für Informatik e. V.
dc.relation.ispartofInformatik 2007 – Informatik trifft Logistik – Band 1
dc.relation.ispartofseriesLecture Notes in Informatics (LNI) - Proceedings, Volume P-109
dc.titleTexture-based Surface Segmentation Using Second-order Statistics of Illumination Seriesen
dc.typeText/Conference Paper
gi.citation.endPage37
gi.citation.publisherPlaceBonn
gi.citation.startPage32
gi.conference.date24.-27. September 2007
gi.conference.locationBremen
gi.conference.sessiontitleRegular Research Papers

Dateien

Originalbündel
1 - 1 von 1
Lade...
Vorschaubild
Name:
32.pdf
Größe:
508.78 KB
Format:
Adobe Portable Document Format