Font Size: a A A

Research On Tube-type Bottle Image Inspection System Based On Digital Image Processing

Posted on:2007-05-21Degree:MasterType:Thesis
Country:ChinaCandidate:J LiuFull Text:PDF
GTID:2178360212958458Subject:Electronics and Communications Engineering
Abstract/Summary:PDF Full Text Request
The medicine tube-type bottle inspection is an important link in medicine industry. Traditional inspection mode is to inspect by human using lighting, but its precision and speed is difficult to meet our needs. Bottle visual inspection system using optics technology, CCD technology and image processing technology can inspect tube-type bottle without any touch. It is provided with the advantage of high speed and high precision. Moreover it can overcome the disadvantage of human's eyes and improve greatly production efficiency and automation degree.The research aiming at the design of a tube-type bottle image inspecting system based on image processing.The main contributions of this dissertation are the followings.Firstly, the structure of the inspecting system was introduced.Aiming at the chatacteristic of medicine tube-type bottle inspection, the dissertation discussed the project as a whole, the selection of acquisition equipment, designing of illumination apparatus and control system.Secondly, a detailed analysis was done to the main process of the inspecting system. Digital images of glass container were collected by CCD camera.The digital images were treated by images processing system and finally were recognized. The inspecting principle was elabotated aiming at the bottle-mouth, bottle-body and the bottle-bottom.Thirdly, a novel filtering method based on mathematics morphology was used in image processing which has better performance than commonly used algorithms. An extremum basing on edge detection algorithm was proposed. The extracted edge obtained by means of this algorithm is the true edge and it has good continuity.
Keywords/Search Tags:Image Processing, Tube-type bottle inspection, Image filtering, Edge detection
PDF Full Text Request
Related items