Automated visual inspection in the semiconductor industry: A survey

Szu-Hao Huang*, Ying Cheng Pan

*Corresponding author for this work

Research output: Contribution to journalReview articlepeer-review

126 Scopus citations

Abstract

Automated visual inspection is an image-processing technique for quality control and production line automation. This paper reviews various optical inspection approaches in the semiconductor industry and categorize the previous literatures by the inspection algorithm and inspected products. The vision-based algorithms that had been adopted in the visual inspection systems include projection methods, filtering-based approaches, learning-based approaches, and hybrid methods. To discuss about the practical applications, the semiconductor industry covers the manufacturing and production of wafer, thin-film transistor liquid crystal displays, and light-emitting diodes. To improve the yield rate and reduce manufacturing costs, the inspection devices are widely installed in the design, layout, fabrication, assembly, and testing processes of production lines. To achieve a high robustness and computational efficiency of automated visual inspection, interdisciplinary knowledge between precision manufacturing and advanced image-processing techniques is required in the novel system design. This paper reviews multiple defect types of various inspected products which can be referenced for further implementations and improvements.

Original languageEnglish
Pages (from-to)1-10
Number of pages10
JournalComputers in Industry
Volume66
DOIs
StatePublished - 1 Jan 2015

Keywords

  • Automated visual inspection
  • LED
  • Semiconductor industry
  • TFT-LCD
  • Wafer

Fingerprint Dive into the research topics of 'Automated visual inspection in the semiconductor industry: A survey'. Together they form a unique fingerprint.

Cite this