NN Automated Defect Detection Based on Optimized Thresholding

  • Hugo Peres Castilho
  • João Rogério Caldas Pinto
  • António Limas Serafim
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4142)


This paper presents a new contribution for the problem of automatic visual inspection. New methods for determining threshold values for fabric defect detection using feedforward neural networks are proposed. Neural networks are one of the fastest most flexible classification systems in use. Their implementation in defect detection, where a clear classification is needed, requires thresholding the output. Two methods are proposed for threshold selection, statistical analysis of the NN output and confusion matrix based optimization. Experimental results obtained from the real fabric defects, for the two approaches proposed in this paper, have confirmed their usefulness.


Defect Detection Training Image True Negative Confusion Matrix Feedforward Neural Network 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Mitropoulos, P., Koulamas, C., Stojanovic, R., Koubias, S., Papadopoulos, G., Karagiannis, G.: A real-time vision system for defect detection and neural classification of web textile fabric. In: Proccedings of the SPIE Electronic Imaging 1999 Intern. Conference (1999)Google Scholar
  2. 2.
    Tuceryan, M., Jain, A.K.: Texture analysis. In: Handbook of pattern recognition & computer vision, pp. 235–276. World Scientific Publishing Co., Inc., River Edge (1993)Google Scholar
  3. 3.
    Stojanovic, R., Koubias, S., Papadopoulos, G.: A comparison of statistical and spectral analytical methods for feature extraction in the process of web defect detection. In: Proccedings of the 3rd International ICSC Symposia on Intelligent Industrial Automation (IIA1999) and Soft Computing (SOCO 1999) (1999)Google Scholar
  4. 4.
    Stojanovic, R., Mitropulos, P., Kouiamas, C., Koubias, S., Papadopoulos, G., Karayanis, G.: Automated detection and neural classification of local defects in textile web. In: Proceedings of the IEE 7th Internanional Conference on Image Processing and its Applications (IPA 1999) (Conf. Publ.No. 465), vol. 2, pp. 647–651 (1999)Google Scholar
  5. 5.
    Karayiannis, G., Stojanovic, R., Mitropoulos, P., Koulamas, C., Stouraitis, T., Koubias, S., Papadopoulos, G.: Defect detection and classification on web textile fabric using multiresolution decomposition and neural networks. In: Proceedings on the 6th IEEE International Conference on Electronics, Circuits and Systems, pp. 765–768 (1999)Google Scholar
  6. 6.
    Stojanovic, R., Mitropulos, P., Koulamas, C., Karayiannis, Y., Koubias, S., Papadopoulos, G.: Real-time vision-based system for textile fabric inspection. Real-Time Imaging 7(6), 507–518 (2001)MATHCrossRefGoogle Scholar
  7. 7.
    Kumar, A., Pang, G.K.H.: Defect detection in textured materials using gabor filterss. IEE Transactions on Industry Applications 38(2) (2002)Google Scholar
  8. 8.
    Kumar, A., Pang, G.K.H.: Defect detection in textured materials using optimized filters. IEE Transactions on Systems, Man, and Cybernetics–Part B: Cybernetics 35(5) (2002)Google Scholar
  9. 9.
    ho Chan, C., Pang, G.K.H.: Fabric defect detection by fourier analysis. IEE Transactions on Industry Applications 36(5) (2000)Google Scholar
  10. 10.
    Randen, T., Husøy, J.H.: Filtering for texture classification: A comparative study. IEEE Transactions on Pattern Analysis and Machine Inteligence 21(4) (1999)Google Scholar
  11. 11.
    Sobral, J.L.: Leather inspection based on wavelets. In: Marques, J.S., Pérez de la Blanca, N., Pina, P. (eds.) IbPRIA 2005. LNCS, vol. 3523, pp. 682–688. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  12. 12.
    Kumar, A.: Neural network based detection of local textile defects. Pattern Recognition Letters 36(7), 1645–1659 (2003)Google Scholar
  13. 13.
    Sari-Sarraf, H., Goddard Jr., J.S.: Robust defect segmentation in woven fabrics. In: CVPR 1998: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, p. 938. IEEE Computer Society Press, Washington (1998)Google Scholar
  14. 14.
    Karras, D.A., Karkanis, S.A., Mertzios, B.G.: Supervised and unsupervised neural network methods applied to textile quality control based on improved wavelet feature extraction techniques. International Journal of Computer Mathematics 67(1), 169–181 (1998)MATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Hugo Peres Castilho
    • 1
  • João Rogério Caldas Pinto
    • 1
  • António Limas Serafim
    • 2
  1. 1.Instituto Superior Técnico/IDMEC 
  2. 2.INETI, Instituto Nacional de Engenharia Tecnologia e Inovação 

Personalised recommendations