Defect Detection in Random Colour Textures Using the MIA T2 Defect Maps
In this paper we present a new approach for the detection of defects in random colour textures. This approach is based on the use of the T2 statistic and it is derived from the MIA strategy (Multivariate Image Analysis) developed in recent years in the field of applied statistics. PCA analysis is used to extract a reference eigenspace from a matrix built by unfolding the RGB raw data of defect-free images. The unfolding is performed compiling colour and spatial information of pixels. New testing images are also unfolded and projected onto the reference eigenspace obtaining a score matrix used to compute the T2 images. These images are converted into defect maps which allow the location of defective pixels. Only very few samples are needed to perform unsupervised training. With regard to literature, the method uses one of the simplest approaches providing low computational costs.
KeywordsDefect Detection Training Image Local Binary Pattern Colour Texture Cumulative Histogram
Unable to display preview. Download preview PDF.
- 6.Kyllönen, J., Pietikänien, M.: Visual inspection of parquet slabs by combining color and texture. In: IAPR Workshop on Machine Vision Applications (MVA 2000), pp. 187–192 (2000)Google Scholar
- 11.Xie, X., Mirmehdi, M.: Localising surface defects in random colour textures using multiscale texem analysis. In: International Conference on Image Processing (ICIP 2005), pp. 1124–1127 (2005)Google Scholar
- 12.Geladi, P., Granh, H.: Multivariate Image Analysis. Wiley, Chichester, England (1996)Google Scholar
- 13.Bharati, M.H., MacGregor, J.F.: Texture analysis of images using Principal Component Analysis. In: SPIE/Photonics Conference on Process Imaging for Automatic Control, pp. 27–37 (2000)Google Scholar
- 14.Prats-Montalbán, J.M., Ferrer, A.: Integration of spectral and textural information in Multivariate Image Analysis. Part 1: On-line process monitoring for visualizing defects on image data. Journal of Chemometrics (submitted)Google Scholar
- 15.Prats-Montalbán, J.M., Ferrer, A.: Integration of spectral and textural information in Multivariate Image Analysis. Part 2: Optimisation of classification models. Journal of Chemometrics (submitted)Google Scholar