SMT Components Model Inspection Based on Characters Image Matching and Verification

Author

Bing Luo ; Yuehua Gao ; Zhongyu Sun ; Sufang Zhao

Author_Institution

Sch. of Inf. Eng., Wuyi Univ., Jiangmen, China

fYear

2013

fDate

20-23 Aug. 2013

Firstpage

1438

Lastpage

1441

Abstract

In PCB SMT assemble automatic inspection, components model should be inspected by their character image. Conventional inspection method suffered from high false detection rate, particularly for same model components with different fonts. Improved method was proposed with position correction, quick image matching and ANN based verification for components with different fonts. Experimental results show the method greatly lower the false detection rate with zero missing rate and quick inspection speed.

Keywords

automatic optical inspection; character recognition; image matching; printed circuit manufacture; production engineering computing; surface mount technology; ANN based verification; PCB SMT assemble automatic inspection; SMT components model inspection; characters image matching; characters image verification; position correction; Artificial neural networks; Assembly; Character recognition; Correlation; Image matching; Image segmentation; Inspection; ANN; OCR; OCV; image matching; surface mounted technology;

fLanguage

English

Publisher

ieee

Conference_Titel

Green Computing and Communications (GreenCom), 2013 IEEE and Internet of Things (iThings/CPSCom), IEEE International Conference on and IEEE Cyber, Physical and Social Computing

Conference_Location

Beijing

Type

conf

DOI

10.1109/GreenCom-iThings-CPSCom.2013.252

Filename

6682264