Research On Fluoride Plastic Film On-line Defect Inspection Based On Multi-linear CCD

Fluoride plastic is more and more widely used in industrial production,because it has the advantages of high temperature, anti-friction,corrosion-resistant,high strength and good insulation.In the production of fluoride plastic film,defects on the surface of the film are the key factors that affect the quality.The traditional defect detection is mainly done by artificial means.Because of human factors and the impact of outside interference,the traditional test of the quality is low-speed,low efficiency,high rate of missing inspection.Therefore it is imperative that on-line inspection system based on machine vision replaces the traditional manual quality testing.In this paper,on the research background of defect inspection system in the production of fluoride plastic film,it firstly discusses the design of on-line defect inspection system.Then it presents an online inspection scheme which uses multi-linear CCD to collect data in parallel, coordinating with selective pixel level image fusion algorithm,two-step strategy of rough detection and fine detection.In the selective pixel level image fusion algorithm,if there are no defects in the image,it will not do image fusion.Otherwise it will do image fusion.There are no defects in most areas,so this article chooses two-step strategy of rough detection and fine detection.Rough detection uses standards-based matching method to determine the existence of defects,fine detection includes positioning and clustering.At last,the software of fluoride plastic film on-line defect inspection system is simulated by Visual C++6.0.Test result shows that it is a practical and fit defects inspection scheme.It can meet the need of fluorine plastic film on-line inspection.