In this paper, a novel idea is proposed for fabric defect detection. De- fects are detected in the fabric using steerable pyramid along with a defect detection algorithm. Various steerable pyramid of four size 256*256, 128*128, 64*64, 32*32 and with four orientation bands 00,450, 900, 1350 are used. Utilizing a Steerable pyramid proved ade- quate in the representation of fabric images in multi-scale and multi- orientations; thus allowing defect detection algorithms to run more effectively. Defect detection algorithm identifies and locates the im- perfection in the defective sample using the statistics mean and stan- dard deviation. This statistics represents the relative amount of inten- sity in the texture and is sufficient to measure defects in the current model .The obtained result are compared with the existing methods wavelet based system and with Gaussian and Laplacian pyramid.
S. Mythili
United Institute of Technology,
Fabric Automatic Visual Inspection, Steerable Pyramid, Feature Extractor, Defect Detector | Published By :
ICTACT
Published In :
ICTACT Journal on Image and Video Processing
( Volume: 1 , Issue: 4 )
Date of Publication :
May 2011
|