Font Size: a A A

The Research On Machine Vision Inspection System For Visible Foreign Substances In Oral Liquid

Posted on:2013-03-13Degree:MasterType:Thesis
Country:ChinaCandidate:J L ZhouFull Text:PDF
GTID:2248330374991369Subject:Control Science and Engineering
Abstract/Summary:PDF Full Text Request
With the development of modern industry technology and the improvement ofliving standard, consumers put forward higher request to the quality and quantity ofproducts. To meet the requirement of quality control in the pharmaceutical industry,nowadays more and more enterprises want to develop the high-speed and automaticproduction line. Take the oral liquid packed in cylindriod vial as the research object,a kind of intelligent vision inspection system is developed, which can liberate theproductivity, advance the production efficiency and ensure the product quality.First, the background and the significance of this research are introduced.Afterwards the concept of machine vision is described. Applications among theindustry and living and the developing trends are presented. The research onautomated inspection equipment is described and the advantages compared with theartificial inspection are analyzed.Secondly, by analyzing the characteristics of the target which has beeninspected, an available scheme for image forming is designed and vision imageforming system is analyzed. The core device for image inspection is introduced,including lighting source, optical lens and industrial camera, device selection isconducted afterward. The vision inspection key technology is analyzed and designed,including image acquisition scheme, system working process, camera shooting modeand sorting apparatus, through the method of multiple inspection in detecting station,inspection error is eliminated. Finally, how to design the mechanical and electricalcontrol system is introduced.Then, shooting images of visible foreign substances in oral liquid are studied,histogram in the image is analyzed and the features of foreign substances areobtained. The inspection difficulties of visible foreign substances are analyzed,visible foreign substances is too small as a target, and there are all kinds ofinterference information. Mathematical modeling and research for foreignsubstances motion trajectory are conducted, through study on dynamics andkinematics of the foreign substances, the movement rule of foreign substances isacquired, the experimental data prove the validity of the analysis. Process of thevisible foreign substances inspection is introduced, various kinds of interferenceinformation are gradually eliminated, and visible foreign body is derived finally.Oral liquid image preprocessing steps before multiple frame image processing are introduced, first using weighted median filter method to eliminate noise, and thenthe inspection region is calibrated.Furthermore, the visible foreign substances inspecting and identifying methodis expounded, this paper analyzes the existing visible foreign substancessegmentation method and introduces the frame differential method and its improvingmethod, in view of the visible foreign substances segmentation in oral liquid, thepaper puts forward complex difference method. In visible foreign substancesdetecting link, adaptive threshold method is used to make binary image, thenconnected regional analysis is conducted, finally discrete line is filled afterconnected domain analysis. In visible foreign substances inspecting link, due to theshape change of plane image caused by the movement of visible foreign substances,a kind of particle filter tracking algorithm based on weighted feature is proposed,overcoming error tracking by single feature, it can distinguish interference andvisible foreign substances effectively. experiments verify its speed and accuracysatisfy online inspection.Finally,the software for visible foreign substances inspecting system in oralliquid is designed,including software general structure design and the interfacedesign, the interface design include state monitoring, parameter setting, inspectionsetting and the result show. The communication system between PC and PC, PC andPLC is developed. A detailed illustration of image acquisition system is made.
Keywords/Search Tags:Machine vision, Oral liquid, Visible foreign substances, Targetinspection, Paticle filter
PDF Full Text Request
Related items