Abstract
Defect detection of textiles is a necessary requirement for quality control and customer satisfaction. This paper presents a system for decision fusion in order to enhance the accuracy of defect detection in textiles. A multi-classifier decision fusion technique based on majority voting is presented to solve the problems of sensitivity to parameter variation and to make use of the advantages of the individual feature sets for accurate texture characterization. Features based on Gray Level Co-occurrence Matrix (GLCM), Laws Energy (LE) Filter, Local Binary Patterns (LBP), HU Moment invariants, Moment of Inertia (MOI) and Standard Deviation of Gray levels are used to train a set of Learning Vector Quantization (LVQ) classifiers. Detection accuracies of classifiers trained on single-feature sets are compared with those of the majority voting among the individual classifiers. The results obtained from majority voting indicate that the decision fusion technique improves the accuracy and reliability of the detection process. Empirical results indicate the high accuracy of the presented approach. The correct defect detection rate of the proposed approach is 98.64% with an average false acceptance rate of 0.0012.
| Schicktanz, K., "Automatic Fault Detection Possibilities on Nonwoven Fabrics", Melliand Textilberichte, 74, 294-295 (1993). Google Scholar | |
| Xie, X., "A Review of Recent Advances in Surface Defect Detection using Texture analysis Techniques", Electronic Letters on Computer Vision and Image Analysis, 7(3), 1-22 ( 2008). Google Scholar | |
| Kumar, A., "Computer Vision-based Fabric Defect Detection: A Survey", IEEE Trans. Industrial Electronics, 55(1), 348-363 (2008). Google Scholar, Crossref | |
| Chen, C.-M., Chen, C.-C., and Chen, C.-C., "A Comparative Study of Texture Features Based on SVM and SOM", Int. Conf. Pattern Recognition, 2006, pp. 630-633. Google Scholar | |
| Cuenca, S.A., and Cámara, A. , "New Texture Descriptor for High-Speed Inspection Applications", International Conference on Image Processing, Barcelona, Spain, September 14-17, (2003). Google Scholar | |
| Monadjemi, A. , Towards Efficient Texture Classification and Abnormality Detection. PhD thesis, University of Bristol , UK, (2004). Google Scholar | |
| Randen, T., and Husoy, J.H., "Filtering for Texture Classification: A Comparative Study", IEEE Transactions on PAMI, 21(4), 291-310 ( 1999). Google Scholar, Crossref | |
| Xie, X., and Mirmehdi, M., "Texems: Random Texture Representation and Analysis", in Handbook of Texture Analysis. Mirmehdi, M., Xie, X., and Suri, J., (eds.), pp. 95-128. (2008). Google Scholar, Crossref | |
| Ohanian, P., and Dubes, R., Performance Evaluation for Four Classes of Textural Features, Pattern Recognition, 25(8), 819- 833 ( 1992). Google Scholar, Crossref | |
| Chang, K., Bowyer, K., and Sivagurunath. M. , "Evaluation of texture segmentation algorithms." In IEEE Conference on Computer Vision and Pattern Recognition , 1, 294-299 (1999). Google Scholar | |
| Drimbarean, A. , and Whelan, P., "Experiments in Color Texture Analysis", Pattern Recognition Lett. 22, 1161-1167 (2001 ). Google Scholar, Crossref | |
| Karoui, I., Fablet, R., Boucher, J.-M., Pieczynski, W., and Augustin, J.-M., "Fusion of Textural Statistics Using A Similarity Measure: Application to Texture Recognition and Segmentation", Pattern Analysis Applications 11, 425-434, (2008). Google Scholar, Crossref | |
| Hadjidemetriou, E., Grossberg, M.D., and Nayar, S.K., "Multiresolution Histograms and their Use for Texture Classification", IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(7), 831-847 (2004). Google Scholar, Crossref, Medline | |
| Najar, S.S., Ghazi Saeidi, R., Latifi, M., Ghazi Saeidi, A., and Rezaei, A.H., "Detecting Defects in Weft-knitted Fabrics Using Texture-Recognition Methods" , Res. J. Textile Apparel, 8(2), (2004). Google Scholar, Crossref | |
| Tolba, A.S. , Khan H.A., and Raafat, H.M., "Feature Fusion for Defect Detection in Flat Surface Products, ISSPIT’2009, Ajman, UAE. Google Scholar | |
| Deselaers, T. , Keysers, D., and Ney, H., "Features for Image Retrieval: A Quantitative Comparison", in DAGM 2004, Pattern Recognition, 26th DAGM Symposium, Tübingen, Germany, volume LNCS3175 of Lecture Notes in Computer Science, pages 228-236, August/September, ( 2004). Google Scholar | |
| Cheng, H.D., and Sun, Y., "A Hierarchical Approach to Color Image Segmentation Using Homogeneity", (1999). Google Scholar | |
| Tilda, "Textile Defect Image Database", University of Freiburg, Germany http://lmb.informatik.unifreiburg.de/research/dfgtexture/tilda . Google Scholar | |
| Mak, K.L. , and Peng P., "Detecting Defects in Textile Fabrics with Optimal Gabor Filters", Proc. World Acad. Sci. Technol., 13, 1307-6884 (2006). Google Scholar | |
| Alameldin, A.S. , "Computer Vision for Automated Inspection of Homogeneous Textures: Methodology for Feature Extraction and Classification" , Wuppertal University, Germany, (1988 ). Google Scholar | |
| Tolba, A.S. , and Abu-Rezeq, A.N. "A Self-Organizing Feature Map for Automated Visual Inspection of Textile Products", Computers in Industry , 32(3), 319-333 (1997). Google Scholar, Crossref | |
| Haralick, R.M. , Shanmugam K., and Dinstein, I., "Textural Features for Image Classification ", SMC- 3, 6, 611-621 ( 1973). Google Scholar | |
| Miyamoto, E., and Merryman Jr, .T. , "Fast calculation of Haralick texture features" , http://www.ece.cmu.edu/~pueschel/teaching/18-799B-CMU-spring05/material/eizan-tad.pdf . Google Scholar | |
| Laws, K.I., "Textured Image Segmentation", Ph.D. thesis, Dept. Electrical Engineering, University of Southern California, January (1980). Google Scholar, Crossref | |
| Laws, K.I., Texture Energy Measures. Proc. Image Understanding Workshop , pp. 41-51, (1979). Google Scholar | |
| Hu, M.K. , "Visual Pattern Recognition by Moment Invariants", IRE Trans. Info. Theory, 8, 179-187 (1962). Google Scholar, Crossref | |
| Flusser, J. , "On the Independence of Rotation Moment Invariants ", Pattern Recognition, 33, 1405-1410 (2000 ). Google Scholar, Crossref | |
| Ojala, T., Pietikäinen, M., and Harwood, D., "A Comparative Study of Texture Measures with Classification Based On Feature Distributions", Pattern Recognition, 29(1), 51-59 (1996). Google Scholar, Crossref | |
| Pietikäinen, M., and Ojala, T., "Nonparametric Texture Analysis with Simple Spatial Operators, Proc. 5th International Conference on Quality Control by Artificial Vision", Trois-Rivieres, Canada, pp. 11-16, (1999). Google Scholar | |
| Mäenpää, T.:, "The Local Binary Pattern Approach to Texture Analysis-Extensions and Applications." PhD Thesis. University of Oulu, (2003). Google Scholar | |
| Flusser, J. , and Suk, T., "Rotation Moment Invariants for Recognition of Symmetric Objects", IEEE Trans. Image Proc., 15, 3784-3790 (2006). Google Scholar, Crossref, Medline | |
| Kohonen, T. , "Self-Organizing Formation of Topologically Correct Feature Maps." Biological Cybernetics, 43(1), 59-69 (1982). Google Scholar, Crossref | |
| Fausett, L., "Fundamentals of Neural Networks", Prentice Hall , (1994). Google Scholar | |
| Lu, X., Wang, Y., and Jain, A.K., "Combining Classifiers for Face Recognition", Proc. ICME 2003, IEEE International Conference on Multimedia and Expo, Baltimore, MD, 3, 13-16, (2003). Google Scholar | |
| Kittler, J. , Hatef, M., Duin, R., and Matas, J., "On Combining Classifiers", IEEE Trans. PAMI, 20(3), 226-239 ( 1998). Google Scholar, Crossref | |
| Lotte, F., Congedo, M., Lecuyer, A., Lamarche, F., and Arnaldi, B., "A Review of Classification Algorithms for EEG-Based Brain-Computer Interfaces" , J. Neural Eng. 4, ( 2007). Google Scholar, Crossref, Medline | |
| Rakotomamonjy, A., Guigue, V., Mallet, G., and Alvardo, V., "Ensemble of SVMs for Improving Brain Computer Interface p300 Speller Performances", Int. Conf. on Artificial Neural Networks, (2005). Google Scholar | |
| Huffmann, U., Garcia, G., Vesin, J-M., Diserens, K., and Ebrahimi, T., 2005 "A Boosting Approach to P300 Detection with Application to Brain-Computer Interfaces", Conference Proc. 2nd Int. IEEE EMBS Conference on Neural Engineering, (2005). Google Scholar | |
| Hong, L., and Jain, A.K., "Integrating Faces and Fingerprint for Personal Identification", IEEE Trans. Pattern Analysis and Machine Intelligence, 20(12), 1295-1307 (1998). Google Scholar, Crossref | |
| Jain, A.K., Duin, R.P.W, and Mao, J., "Statistical Pattern Recognition: A Review." IEEE Transactions On Pattern Analysis and Machine Intelligence, 22(1), 3-37 (2000). Google Scholar | |
| Alimoglu, F. , and Alpaydin, E., "Combining Multiple Representations for Pen-Based Handwritten Digit Recognition", Turk. J. Elec. Engin., 9(1), 1-12 (2001). Google Scholar | |
| Shi, M. , Jiang, S., Wang, H., and Xu, B., "A Simplified Pulse-Coupled Neural Network for Adaptive Segmentation of Fabric Defects", Machine Vision and Applications, Vol 20, No 2, (2009). Google Scholar | |
| Sezera, O.G. , Ercilb, A., and Ertuzunc, A., "Using Perceptual Relation of Regularity and Anisotropy in the Texture with Independent Component Model for Defect Detection", Pattern Recognition 40, 121-133 ( 2007). Google Scholar, Crossref | |
| Basi büyük, K. Çoban, K., and Ertüzün , A., "Model Based Defect Detection Problem: Particle Filter Approach", 3rd IEEE International Symposium on Communications, Control and Signal Processing (ISCCSP 2008), St Juliens, Malta, March 12-14, (2008). Google Scholar | |
| Murino, V., Bicego, M., and Rossi, I.A., "Statistical Classification of Raw Textile Defects", Proc. 17th Intern. Conf. on Pattern Recognition (ICPR’04). Google Scholar | |
| Pieczynski, W., Augustin, J.-M., Karoui, I., Fablet, R., and Boucher J.-M., "Fusion of Textural Statistics Using A Similarity Measure: Application to Texture Recognition and Segmentation", Pattern Anal. Applic. 11, 425-434 (2008). Google Scholar, Crossref | |
| Jenicka, S., and Suruliandi, A., "Comparative Study of Texture models Using Supervised Segmentation" , ADCOM, (2008). Google Scholar | |
| Hu, Y.H., "Face Recognition: Opportunities and Challenges", Microsoft Research, March 17, (2006). Google Scholar | |
| Perrone, M.P. "Improving Regression Estimation: Averaging Methods for Variance Reduction with Extensions to General Convex Measure Optimization", Ph. D. Thesis, Department of Physics, Brown University , (1999). Google Scholar | |
| Hansen, L.K. , and Salamon, P., "Neural Network Ensembles", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 12, No. 10, (1990 ). Google Scholar |
