View : 98 Download: 0

Deep Learning Based Defect Inspection Using the Intersection Over Minimum Between Search and Abnormal Regions

Title
Deep Learning Based Defect Inspection Using the Intersection Over Minimum Between Search and Abnormal Regions
Authors
Choi E.Kim J.
Ewha Authors
김정태
SCOPUS Author ID
김정태scopus
Issue Date
2020
Journal Title
International Journal of Precision Engineering and Manufacturing
ISSN
2234-7593JCR Link
Citation
International Journal of Precision Engineering and Manufacturing
Keywords
Deep learningDefect inspectionMachine visionObject detection
Publisher
SpringerOpen
Indexed
SCIE; SCOPUS; KCI scopus
Document Type
Article
Abstract
We present a deep learning based defect inspection system that detects bounding boxes for any identified defect regions. In contrast to existing deep learning based object detection methods, the proposed method detects defects based on the intersection over minimum between a proposal region and defect regions rather than the well-known intersection over union, since intersection over minimum is more effective to detect variously sized defects. The proposed method also provides significant improvements over existing methods such as efficient training by minimizing cross entropy loss function, and efficient defect detection using multiple proposal boxes for the defect and entire image. We verified that the proposed method provides improved performance compared with existing methods using simulation and experimental studies. © 2020, Korean Society for Precision Engineering.
DOI
10.1007/s12541-019-00269-9
Appears in Collections:
엘텍공과대학 > 전자공학과 > Journal papers
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE