Classifying Web Defects with a Back-Propagation Neural Network by Color Image Processing

Abstract

The aim of this research is to construct an appropriate back-propagation neural network topology to automatically recognize neps and trash in a web by color image processing. After studying the ideal background color under moderate conditions of brightness and contrast to overcome the translucent problem of fibers in a web, specimens are reproduced in a color BMP image file format. Assuming that neps and trash can be distinguished without difficulty from the color image, the image-taking device in the system can be easily altered as long as the optical conditions for other color image resources (i.e., CCD) are considered to ensure image quality. With a back-propagation neural network, the RGB (red, green, and blue) values corresponding with the image pixels are used to perform the recognition, and three categories (i.e., normal web, nep, and trash) can be recognized. The numbers and areas of both neps and trash can also be determined. According to experi mental analysis, the recognition rate can reach 99.63% under circumstances in which the neural network topology is 3-3-3. Both contrast and brightness are set at 60% with an azure background color. The results show that both neps and trash can be recognized well, and the method is suitable not only for cotton and man-made fibers of different lengths, but also for different web thicknesses as to a limit of 32.9 g/m². Since neps and trash in a web can be recognized, yarn quality not only can be assessed but also improved using a reference for adjusting manufacturing parameters.

Get full access to this article

View all access options for this article.

References

Chen, P.W. , Liang, T.C. , Yau, H.F. , Sun, W.L. , Wang, N.C. , Lin, H.C. , and Lien, R.C. , Classifying Textile Faults with a Back-Propagation Neural Network Using Power Spectra, Textile Res. J. 68 (2), 121-126 (1998).

Dhawan, A.P. , and Sicsu, A. , Segmentation of Images of Skin Lesions Using Color and Information of Surface Pigmentation, Comput. Med. Imag. Graph. 16, 163-177 (1992).

Fan, K.C. , Wang, Y.K. , Chang, B.L. , Wang, T.P. , Jou, C.H. , and Kao, I.F. , Fabric Classification Based on Recognition Using a Neural Network and Dimensionality Reduction, Textile Res. J. 68(3), 179-185 (1998).

Foresee, F.D. , Hagan, M.T. , Gauss-Newton Approximation to Bayesian Regularization, in "Proc. 1997 International Joint Conference on Neural Networks," 1997, pp. 1930-1935.

Gonzalez, R.C. , and Wood, R.E. , "Digital Image Processing," Addison-Wesley, NY , 1992.

Huang, C.L. , Huang, Y.H. , Chang, T.Y. , Chang, S.H. , Chung, C.H. , Huang, D.T. , and Li, R.K. , The Construction of a Production Performance Prediction System for Semiconductor Manufacturing with Artificial Neural Networks, Int. J. Product. Res. 37 (6), 1387-1402 (1999).

Li, T.W. , An Application of Color Images for Leadframe Quality Inspection, Master's thesis, Yuan-Ze University, Taiwan, R.O.C., 1998.

Lin, J.J. , Lin, C.H. , and Tsai, I.S. , Applying Expert System and Fuzzy Logic to an Intelligent Diagnosis System for Fabric Inspection, Textile Res. J. 65 (12), 697-709 (1995).

Pao, Y.H. , "Adaptive Pattern Recognition and Neural Networks," Addison-Wesley, Reading, MA, 1989 .

10.

Raafat, H. , and Taboun, S. , An Integrated Robotics and Machine Vision System for Surface Flaw Detection and Classification, Comput. Ind. Eng . 30, 27-40 (1996).

11.

Rajasek, A.S. , Training-Free Propagation Neural Network for Pattern Recognition of Fabric Defects, Textile Res. J. 67 (6), 401-405 (1997).

12.

Sharm, Gaurau , and Trussell, H. Joel , Digital Color Imaging, IEEE Trans. Image Proc. 6 , 901-933 (1997).

13.

Tsai, I.S. , and Hu, M.C. , Automatic Inspection of Fabric Defects Using an Artificial Neural Network Technique, Textile Res. J. 66 (7), 474-482 (1996).

14.

Tsai, I.S. , Lin, C.H. , and Lin, J.J. , Applying an Artificial Neural Network to Pattern Recognition in Fabric Defects , Textile Res. J. 65 (3), 123-130 (1995).

15.

Tsai, I.S. , Liu, J.Y. , Chiou, H.H. , and Yao, S.C. , A Study on the Appearance Area of Nep and Automatic Nep Counting , J. China Textile Inst. 5 (6), 396-404 (1995).

16.

Viaplana, A. , A New Electronic Device for Counting and Classifying Neps in Card Web, Textile Res. J. 34 (7), 675-681 (1964).