We present an application of a Training-free counter propagation network (tfcpn) to detect fabric defects. The TFCPN, which is a modification of Hecht-Nielsen's counter propagation network (cpn), learns through a simple recording algorithm devoid of any training, while retaining the topology of the cpn model. The mathematical justification for the modification is also presented. Four kinds of fabric defects—neps, broken ends, broken picks, and oil stains—most likely to be found during weaving are considered for recognition by the network. Results show that fabric defects such as these inspected by means of image recognition in accordance with the tfcpn agree approximately with initial expectations. The cpn reported in this paper is training-free, and it can learn complicated textile design problems.
Get full access to this article
View all access options for this article.
References
1.
AdeliH.ParkH. S., Counter Propagation Neural Networks in Structural Engineering, J. Structural Eng. ASCE121 (8), 1205–1212 (1995).
2.
CarpenterG. A.GrossbergS., A Massively Parallel Architecture for a Self Organizing Neural Pattern Recognition Machine, Computer Vision Graph. Image Proc.37, 54–115 (1977).
3.
DeshpandeJ. M.MukherjeeA., Artificial Neural Networks in Initial Design of RC Beams, in “Proc. International Conference on Computational Methods in Engineering,” Shiraz, Iran May 1993.
4.
GhaboussiJ.JoghatieA., Active Control of Structures using Networks, ASCE J. Eng. Mech. Div. 121 (4), 555–567 (1995).
5.
GrossbergS., “Studies of Mind and Brain,” Reidel Press, Boston, MA, 1982.
6.
HollandJ. H., “Adaptation in Natural and Artificial Systems,” University of Michigan Press, Ann Arbor, MI, 1975.
7.
KohonenT., “Self Organization and Associative Memory,” Springer Verlaag, NY, 1988.
8.
KohonenT., The Self Organizing Map, Proc. IEEE78 (9), 1464–1480 (1990).
9.
LippmannR. P., An Introduction to Computing with Neural Nets, IEEE Mag, Acoustic Signal Speech Proc. (4), 4–22 (1987).
10.
LiuX.GanM., “A Preliminary Design Expert System (SPREAD-1) Based on Neural Network,” Artificial Intelligence in Design, Butterworth-Heineman Ltd, Oxford, U.K., 1991, pp. 785–800.
PrameelaH. S., Artificial Neural Networks in Civil Engineering, Masters thesis submitted to the Bharathiar University, Coimbatore, 1996.
14.
RajasekaranS., Computing with Words Using Fuzzy Back Propagation Training Free Counter Propagation Network, J. Structural Eng. (accepted for publication).
15.
RajasekaranS.RamasamyJ. V.FebinM. F., Artificial Neural Networks for Preliminary Area of Truss Configuration, in Proc. National Conference on Civil Engineering Materials and Structures, 1995, 402–408.
16.
TsaiI. S.LinC. H.LinJ. J., Applying an Artificial Neural Network to Pattern Recognition in Fabric Defects, Textile Res. J. 65 (3), 123–130 (1995).
17.
Van LuchineR. D.RouffeiS., Neural Networks in Structural Engineering, Micro Computers Civil Eng.5, 207–215 (1990).
18.
WassermanP. O. D., “Neural Computing: Theory and Practice,” Von Nostrand Reinhold, NY, 1989.
