View : 40 Download: 0

A comparative study of transfer learning-based methods for inspection of mobile camera modules

Title
A comparative study of transfer learning-based methods for inspection of mobile camera modules
Authors
Choi E.Jo H.Kim J.
Ewha Authors
김정태
SCOPUS Author ID
김정태scopus
Issue Date
2018
Journal Title
IEIE Transactions on Smart Processing and Computing
ISSN
2287-5255JCR Link
Citation
IEIE Transactions on Smart Processing and Computing vol. 7, no. 1, pp. 70 - 74
Keywords
Camera moduleDefect inspectionMachine visionTransfer learning
Publisher
Institute of Electronics and Information Engineers
Indexed
SCOPUS; KCIE scopus
Document Type
Article
Abstract
We apply three transfer learning methods using the pretrained AlexNet convolutional neural network (CNN) model to detect defects in camera modules. In experiments, the performance of fine-tuning methods using random initial parameters in less than the two last fully connected layers while using predetermined weights as initial parameters for the remaining layers, showed better performance than other methods. We expect that the transfer learning-based CNN can be effectively applied to camera module inspection systems. © 2018 The Institute of Electronics and Information Engineers.
DOI
10.5573/IEIESPC.2018.7.1.070
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