Defect Detection of Tiles Using 2D-Wavelet Transform and Statistical Features

In this article, a method has been offered to classify normal and defective tiles using wavelet transform and artificial neural networks. The proposed algorithm calculates max and min medians as well as the standard deviation and average of detail images obtained from wavelet filters, then comes by feature vectors and attempts to classify the given tile using a Perceptron neural network with a single hidden layer. In this study along with the proposal of using median of optimum points as the basic feature and its comparison with the rest of the statistical features in the wavelet field, the relational advantages of Haar wavelet is investigated. This method has been experimented on a number of various tile designs and in average, it has been valid for over 90% of the cases. Amongst the other advantages, high speed and low calculating load are prominent.

[1]  K. L. Mak,et al.  An automated inspection system for textile fabrics based on Gabor filters , 2008 .

[2]  C.-C. Jay Kuo,et al.  Texture analysis and classification with tree-structured wavelet transform , 1993, IEEE Trans. Image Process..

[3]  Aysin Ertüzün,et al.  An efficient method for texture defect detection: sub-band domain co-occurrence matrices , 2000, Image Vis. Comput..

[4]  Majid Mirmehdi,et al.  Restructured Eigenfilter Matching for Novelty Detection in Random Textures , 2004, BMVC.

[5]  Gérard Ballivy,et al.  Neural-network-based damage classification of bridge infrastructure using texture analysis , 2008 .

[6]  Nicu Sebe,et al.  Wavelet based texture classification , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[7]  Harsh Potlapalli,et al.  Texture characterization and defect detection using adaptive wavelets , 1996 .

[8]  Michael K. Ng,et al.  Wavelet based methods on patterned fabric defect detection , 2005, Pattern Recognit..

[9]  Jacob D. Furst,et al.  Wavelet-based texture classification of tissues in computed tomography , 2005, 18th IEEE Symposium on Computer-Based Medical Systems (CBMS'05).

[10]  S. Arivazhagan,et al.  Color texture classification using wavelet transform , 2005, Sixth International Conference on Computational Intelligence and Multimedia Applications (ICCIMA'05).

[11]  B. S. Manjunath,et al.  A comparison of wavelet transform features for texture image annotation , 1995, Proceedings., International Conference on Image Processing.

[12]  Z. Hocenski,et al.  Neural network based detection of defects in texture surfaces , 2005, Proceedings of the IEEE International Symposium on Industrial Electronics, 2005. ISIE 2005..

[13]  Robert J. Schalkoff,et al.  Artificial neural networks , 1997 .