Full-Text Search:
Home|About CNKI|User Service|中文
Add to Favorite Get Latest Update

The Tank Mouth Detection Based on Machine Vision

Zhang Hongzhao;Zhou Songbin;Liu Weixin;Guangdong Institute of Automation College of Automation & Guangdong Province,Modem Control and Light Mechanical and Electrical Technology,Guangdong Province Key Laboratory of Modem Control Technology;Guangdong University of Technology;  
This paper proposes a round tin visual detection algorithm.The PSNR and SSIM index of image quality analysis,to obtain a high signal-to-noise ratio,high contrast and clear image in order;image smoothing,filtering,denoising,gray and so on after pretreatment by Otsu method(OTSU) isolated from the mouth region,then apply the findContours OpenCV visual function in the library,detection of binarization image connected domain of the contour,and the contour feature analysis,to accurately determine the bottle contour,then using the least squares fitting ellipse fitting algorithm,mouth contour curve and contour center,finally the fitting ellipse discretization is 360 scan sampling,the sampling point pixel analysis,finally get the deviation analysis with a map,can carry out quantitative analysis and positioning to solve the problem of the gap,the length of mouth angle,deformation etc.
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©CNKI All Rights Reserved