Visual Detection System Design for Plastic Infusion Combinations Containers Based on Reverse PM Diffusion

摘要

Aimed at the defect of black spots, hair, bubbles in medical PP infusion, infusion defect detection system based on machine vision is proposed. Firstly, r design the mechanical actuators, electrical control, and image acquisition system, then use reverse PM diffusion algorithm to enhance the defect area, extracting this area by difference after binarization, and filter the image. Secondly, SVM is used to classify defects and the defective area automatically. Meanwhile, in order to improve the performance of the classifier, the paper selected the best classification parameters based cross validation. The results show that the method is high detection accuracy and requires less training samples, applies to different defect types with accuracy rate of 95%.