Automated Complex Fabric Faults Detection Using A Hybrid Method

Fault detection or identification is highly important to fabric quality control.Traditionally,faults are detected by human eyes.The efficiency of this manual technique is low and the missed rate is high because of eye fatigue.In the best case,a quality control person cannot detect more than 60–70 % of the present faults.In this study a Hybrid technique is developed to identify complex faults of warp-knitted fabrics automatically.In this system,we use smart cameras and a Human Machine Interface(HMI)controller.This hybrid detection or identification algorithm is comprised of numerous single techniques such as Gabor filter,PCNN,morphological filter,and another associated technique(Binarizing)those are running on the SOC processor of the smart camera for identifying distinctive types of complex faults on fabric.First,Gabor filters are employed to enhance the contrast of images captured by a CMOS sensor.If fault is not detected after Gabor filter it goes through Binarization.Second,fault areas are segmented by PCNN with adaptive parameter setting.Third,for making the PCNN output more clear and faults more obvious,the morphological filter has been used in this detection or identification system.Finally,smart cameras will notice the controller to stop the warp-knitting machine once faults are found out.Experimental results demonstrate that the hybrid technique is superior to Gabor and PCNN techniques on fabric complex faults detection or identification accuracy.By this hybrid technique we get 97.08% fault detection or identification accuracy which is superior to Gabor and PCNN techniques.Actual operations in a textile factory can be verified the effectiveness of the inspection system.