A novel method is presented to detect defects in random colour textures which requires only a very few normal samples for unsupervised training. We decorrelate the colour image by generating three eigenchannels in each of which the surface texture image is divided into overlapping patches of various sizes. Then, a mixture model and EM is applied to reduce groupings of patches to a small number of textural exemplars, or texems. Localised defect detection is achieved by comparing the learned texems to patches in the unseen image eigenchannels.
Localising surface defects in random colour textures using multiscale texem analysis in image eigenchannels
IEEE International Conference on Image Processing 2005 ; 3 ; III-1124
2005-01-01
205571 byte
Conference paper
Electronic Resource
English
British Library Conference Proceedings | 2005
|Defect detection in random colour textures
British Library Online Contents | 1996
|Perceptual correction for colour grading of random textures
British Library Online Contents | 2000
|Heteroscedastic Gaussian Processes for Localising Acoustic Emission
British Library Conference Proceedings | 2021
|NGK Spark Plugs | Transferring Technology, Localising Production
Springer Verlag | 2013