Automatic visual inspection using image processing and analysis algorithms enables us to control the production quality of textiles produced. Textiles having a uniform, even complex surface may be analyzed with regard to their irregularities and defects. To detect such defects, singular value decomposition method (SVD) was suggested. This method can precisely distinguish surface images with no defects from images with defects and this distinction consists in the analysis of singularities expressed by specific numbers. Such approach does not require using complex methods, e.g. artificial intelligence using whole sets of numbers. The experiment conducted on several exemplary textiles proves the high efficiency of this method in automatic textile quality control.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.