Logo des Repositoriums
 
Konferenzbeitrag

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

Lade...
Vorschaubild

Volltext URI

Dokumententyp

Text/Conference Paper

Zusatzinformation

Datum

2007

Zeitschriftentitel

ISSN der Zeitschrift

Bandtitel

Verlag

Gesellschaft für Informatik e. V.

Zusammenfassung

Many 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.

Beschreibung

Lindner, Christoph; Schäffler, Fabian; Puente León, Fernando (2007): Texture-based Surface Segmentation Using Second-order Statistics of Illumination Series. Informatik 2007 – Informatik trifft Logistik – Band 1. Bonn: Gesellschaft für Informatik e. V.. PISSN: 1617-5468. ISBN: 978-3-88579-206-1. pp. 32-37. Regular Research Papers. Bremen. 24.-27. September 2007

Schlagwörter

Zitierform

DOI

Tags