Development Of Inspection System For Surface Defects Of Woven Bags Based On Machine Vision

The production of woven bags has been gradually automated,but the detection of surface defects of woven bags is still dominated by manual inspection,which is one of the main bottlenecks restricting the improvement of the production efficiency and quality of woven bags.Machine vision technology has the advantages of high recognition accuracy,fast detection speed and non-contact.Applying it to the surface defect detection of woven bags can effectively solve the shortcomings of manual inspection methods,thereby improving the production efficiency of woven bags.(1)Completed the design of software and hardware system for surface defect detection of woven bags based on machine vision.By analyzing the functions and requirements of the system,the overall plan of the system was designed.The hardware part of the system was designed,including the selection of image acquisition equipment,lighting scheme and camera control device.The software part of the system was designed,including software architecture and human-computer interaction interface.(2)Aiming at the difficulty of uneven background grayscale and large noise in the detection of surface defects of woven bags,a method for detecting surface defects of woven bags based on the two-dimensional maximum entropy method was used.In order to reduce the influence of background gray changes on defect detection,a preprocessing algorithm with both noise filtering and image enhancement functions was studied.Then,the two-dimensional maximum entropy method was selected to segment the woven bag map,and the improved genetic algorithm was used to optimize it to enhance the convergence speed and effect of the algorithm.Finally,morphological processing was used to eliminate structural interference in the segmentation image,and the target area was extracted.(3)Identification and location of surface defects of woven bags.First,the image feature extraction method of connected domain analysis was studied.Then,the method of feature extraction combined with morphological processing was used to realize the recognition and classification of surface defects of woven bags.Finally,the connected domain analysis was used to count and locate the classified defects to obtain the size and location information of the defects.(4)Through the woven bag surface defect detection system to identify defects,the results show that the average accuracy of the defect detection system for various types of defects is 94.0%,which meets the inspection requirements of the woven bag automatic production line.