Title :
Pattern segmentation in textile images
Author :
Smoaca, Andreea ; Coltuc, Daniela ; Lazarescu, Vasile
Author_Institution :
Fac. of Electron., Telecommun. & Inf. Technol., Univ. Politeh. of Bucharest, Bucharest, Romania
Abstract :
This paper presents some results regarding the automatic segmentation of patterns in images of textile samples. The pattern segmentation is necessary for further extraction of a set of shape descriptors to be used in a CBIR database for textiles. Five different filters for removing the fabrics texture have been tested: mean, median, Gaussian, soft wavelet thresholding and a new approach based on wavelet transform and independent components analysis. For segmentation, due to the poor color content of the images, the binarization proved to be a satisfactory choice. Three algorithms for the threshold computation have been tested: Otsu, background symmetry and triangle.
Keywords :
fabrics; feature extraction; image segmentation; image texture; independent component analysis; production engineering computing; textile industry; wavelet transforms; CBIR database; Gaussian wavelet thresholding; fabrics texture removal; filters; independent components analysis; mean wavelet thresholding; median wavelet thresholding; pattern segmentation; shape descriptor set extraction; soft wavelet thresholding; textile images; wavelet transform; Fabrics; Filters; Image databases; Image segmentation; Independent component analysis; Shape; Testing; Textiles; Wavelet analysis; Wavelet transforms;
Conference_Titel :
Signals, Circuits and Systems, 2009. ISSCS 2009. International Symposium on
Conference_Location :
Iasi
Print_ISBN :
978-1-4244-3785-6
Electronic_ISBN :
978-1-4244-3786-3
DOI :
10.1109/ISSCS.2009.5206185
