Defect Inspection in Display Panel Using Concentrated Auto Encoder

In this paper, concentrated auto encoder (CAE) is proposed for aligning photo spacer (PS) and for local inspection of PS. The CAE method has two characteristics. First, unaligned images can be moved to the same alignment position, which makes it possible to move the measured PS images to the same po...

Full description

Bibliographic Details
Main Author: DongHun Ku
Format: Article
Language:English
Published: Hindawi Limited 2019-01-01
Series:International Journal of Optics
Online Access:http://dx.doi.org/10.1155/2019/8039267
id doaj-aff2c9c25ceb45f091a2821428365d53
record_format Article
spelling doaj-aff2c9c25ceb45f091a2821428365d532020-11-25T00:57:18ZengHindawi LimitedInternational Journal of Optics1687-93841687-93922019-01-01201910.1155/2019/80392678039267Defect Inspection in Display Panel Using Concentrated Auto EncoderDongHun Ku0School of Mechanical & Aerospace Engineering/SNU-IAMD, Seoul National University, Seoul 08826, Republic of KoreaIn this paper, concentrated auto encoder (CAE) is proposed for aligning photo spacer (PS) and for local inspection of PS. The CAE method has two characteristics. First, unaligned images can be moved to the same alignment position, which makes it possible to move the measured PS images to the same position in order to directly compare the images. Second, the characteristics of the abnormal PS are maintained even if the PS is aligned by the CAE method. The abnormal PS obtained through CAE has the same alignment as the reference PS and has its abnormal characteristics. The presence or absence of defects and the location of defects were identified without precisely measuring the height of the PS and critical dimension (CD). Also, alignment and defect inspection were performed simultaneously, which shortened the inspection time. Finally, inspection performance parameters and inspection time were analyzed to confirm the validity of the CAE method and were compared with the image similarity comparison methods used for defect inspection.http://dx.doi.org/10.1155/2019/8039267
collection DOAJ
language English
format Article
sources DOAJ
author DongHun Ku
spellingShingle DongHun Ku
Defect Inspection in Display Panel Using Concentrated Auto Encoder
International Journal of Optics
author_facet DongHun Ku
author_sort DongHun Ku
title Defect Inspection in Display Panel Using Concentrated Auto Encoder
title_short Defect Inspection in Display Panel Using Concentrated Auto Encoder
title_full Defect Inspection in Display Panel Using Concentrated Auto Encoder
title_fullStr Defect Inspection in Display Panel Using Concentrated Auto Encoder
title_full_unstemmed Defect Inspection in Display Panel Using Concentrated Auto Encoder
title_sort defect inspection in display panel using concentrated auto encoder
publisher Hindawi Limited
series International Journal of Optics
issn 1687-9384
1687-9392
publishDate 2019-01-01
description In this paper, concentrated auto encoder (CAE) is proposed for aligning photo spacer (PS) and for local inspection of PS. The CAE method has two characteristics. First, unaligned images can be moved to the same alignment position, which makes it possible to move the measured PS images to the same position in order to directly compare the images. Second, the characteristics of the abnormal PS are maintained even if the PS is aligned by the CAE method. The abnormal PS obtained through CAE has the same alignment as the reference PS and has its abnormal characteristics. The presence or absence of defects and the location of defects were identified without precisely measuring the height of the PS and critical dimension (CD). Also, alignment and defect inspection were performed simultaneously, which shortened the inspection time. Finally, inspection performance parameters and inspection time were analyzed to confirm the validity of the CAE method and were compared with the image similarity comparison methods used for defect inspection.
url http://dx.doi.org/10.1155/2019/8039267
work_keys_str_mv AT donghunku defectinspectionindisplaypanelusingconcentratedautoencoder
_version_ 1725224793628737536