In this study, wavelet transform and an artificial neural network (ANN) are used to inspect four kinds of fabric defect. Multiresolution representation of an image by using wavelet transform is a new and effective approach to the analysis of image information content. The transform can be computed efficiently by a pyramidal algorithm. The result is a set of sub-band images that consist of a lower-resolution version of the original image and a sequence of detail sub-images containing higher-spectral information. Since the transform generates localized spatial and frequency information simultaneously, the location and the kind of fabric defect can be inspected. In this study, we calculate the average and standard deviation for each sub-image as feature parameters for ANN. We explore three basic considerations on the classification rate of fabric-defect inspection consisting of wavelets with various maximum vanishing moments, different numbers of resolution levels, and different scaled-fabric images. The results show that the total classification rate for a wavelet function with a maximum vanishing moment of 4 and resolution levels of 3 can reach 100%, and the different-scaled fabric image does not obviously affect the classification rate.
[1]
Eiji Toba,et al.
EXPERT SYSTEM TO INSPECT FABRIC DEFECTS BY PATTERN RECOGNITION
,
1990
.
[2]
Timothy G. Clapp,et al.
An On-Line Fabric Classification Technique Using a Wavelet-Based Neural Network Approach
,
1996
.
[3]
Ingrid Daubechies,et al.
Ten Lectures on Wavelets
,
1992
.
[4]
Stéphane Mallat,et al.
A Theory for Multiresolution Signal Decomposition: The Wavelet Representation
,
1989,
IEEE Trans. Pattern Anal. Mach. Intell..
[5]
I. Tsai,et al.
Automatic Inspection of Fabric Defects Using an Artificial Neural Network Technique
,
1996
.
[6]
I. Daubechies.
Orthonormal bases of compactly supported wavelets
,
1988
.
[7]
Zhigang Fan,et al.
Automated Inspection of Textile Fabrics Using Textural Models
,
1991,
IEEE Trans. Pattern Anal. Mach. Intell..
[8]
Lieven Vangheluwe,et al.
Assessment of Set Marks by Means of Neural Nets
,
1993
.