Texture Exemplars for Defect Detection on Random Textures

Xie Xianghua, M Mirmehdi

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

21 Citations (Scopus)

Abstract

We present a new approach to detecting defects in random textures which requires only very few defect free samples for unsupervised training. Each product image is divided into overlapping patches of various sizes. Then, density mixture models are applied to reduce groupings of patches to a number of textural exemplars, referred to here as texems, characterising the means and covariances of whole sets of image patches. The texems can be viewed as implicit representations of textural primitives. A multiscale approach is used to save computational costs. Finally, we perform novelty detection by applying the lower bound of normal samples likelihoods on the multiscale defect map of an image to localise defects.
Translated title of the contributionTexture Exemplars for Defect Detection on Random Textures
Original languageEnglish
Title of host publicationUnknown
PublisherSpringer Berlin Heidelberg
Pages404 - 413
Number of pages9
Publication statusPublished - Aug 2005

Bibliographical note

Conference Proceedings/Title of Journal: International Conference on Advances in Pattern Recognition

Fingerprint

Dive into the research topics of 'Texture Exemplars for Defect Detection on Random Textures'. Together they form a unique fingerprint.

Cite this