Font Size: a A A

Automatic Defects Inspection System Of Printed Circuit Board Based On Vision

Posted on:2007-03-23Degree:MasterType:Thesis
Country:ChinaCandidate:M H LiuFull Text:PDF
GTID:2178360212957555Subject:Signal and Information Processing
Abstract/Summary:PDF Full Text Request
Nowadays, Printed Circuit Board (PCB) plays an important role in electronic devices. The quality of electronic productions somewhat depends on that of Printed Circuit Board. The defects of components on PCB will effect the production badly. Due to the fatigue, subjectivity and speed requirement, manual inspection is ineffective to inspect every complex board. So there is a badly need of new approaches that can examine components automatically.This paper proposes a new method for automatic component detection by computer. Based on digital image processing, we have studied different features of different components and mainly done the following research:(1) The inspection requires high precision, a method of extracting mark points to locate the image is proposed.(2) Features of RGB and HSI color spaces are studied and chip capacitor inspection is realized by utilizing the color feature.(3) When solder bridge happens, two or more pins of components are connected. It can be saw that in the image the lightness of corresponding region will be higher than normal. In this paper, a method based on connected domain extraction is proposed. The method can inspect the solder bridge successfully.(4) Chip resistors own the same shape and size, the only feature that can distinguish them is the figure on the surface. In this paper, projection feature, structure feature and shape context feature are studied and compared.
Keywords/Search Tags:PCB, Defects Inspection, Color Space, Character Recognition
PDF Full Text Request
Related items