Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Review and outlook for texture analysis methods

: Vogelbacher, Markus

Volltext urn:nbn:de:0011-n-2384779 (283 KByte PDF)
MD5 Fingerprint: 45e6fa61740057ef298e708c17f2df08
Erstellt am: 25.4.2013

Beyerer, Jürgen (Ed.); Pak, Alexey (Ed.) ; Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung -IOSB-, Karlsruhe; Karlsruhe Institute of Technology -KIT-, Lehrstuhl für Interaktive Echtzeitsysteme -IES-:
Joint Workshop of Fraunhofer IOSB and Institute for Anthropomatics, Vision and Fusion Laboratory 2012. Proceedings : Triberg-Nussbach, Germany, July, 22 to 28, 2012
Karlsruhe: KIT Scientific Publishing, 2013 (Karlsruher Schriften zur Anthropomatik 13)
ISBN: 978-3-86644-988-6
DOI: 10.5445/KSP/1000032956
Fraunhofer Institute of Optronics, System Technologies and Image Exploitation and Institute for Anthropomatics, Vision and Fusion Laboratory (Joint Workshop) <2012, Triberg-Nussbach>
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IOSB ()

The description and analysis of textures is a widely discussed topic. Different methods have already been developed but there are still a lot of opportunities to develop new approaches. For this reason, in this report at first an overview of the standard methods for the analysis of textures is given. Based on that, new ideas and opportunities are presented which extend these methods but also represent totally new approaches. In the field of structural statistical textures the change in the structural arrangement scheme is described analogously to the modulation of signals in communications technology. A basic fundament is the representation of an image signal by a two-dimensional extended Fourier series whose parameters can be obtained using unmodulated texture primitives. Another subject is the determination of parameters in the modeling of textures using AR-models. This estimate is carried out using the Support Vector Regression (SVR) and, thus, offers an alternative to the in the field of texture analysis widely used Least-Square (LS) and Maximum-Likelihood (ML) estimation methods. In the field of optical inspection of textiles an approach will be introduced, which enables the assessment of tissue properties and the detection of errors. The assessment is not based on the derivation of features from the methods of texture analysis, but uses the possibilities of the image acquisition by a variable illumination.