Automatic Mura Detection for Display Film Using Mask Filtering in Wavelet Transform

Jong-Seung PARK; Seung-Ho LEE

doi:10.1587/transinf.2014EDL8140

Automatic Mura Detection for Display Film Using Mask Filtering in Wavelet Transform

Jong-Seung PARK, Seung-Ho LEE

Full Text Views

0

Share
Cite this

Summary :

In this letter, we present a method for automatic mura detection for display film using the efficient decision of cut-off frequency with DCT and mask filtering with wavelet transform. First, the background image including reflected light is estimated using DCT with adaptive cut-off frequency, and DWT is applied to background-removed images for generating mura mask. Then, a mura mask is generated by separating low-frequency noise in the approximation coefficients. Lastly, mura is detected by applying mura mask filtering to the detail coefficients. According to the comparison by Semu index, the results from the proposed method are superior to those from the existing methods. This indicates that the proposed method is high in reliability.

Publication: IEICE TRANSACTIONS on Information Vol.E98-D No.3 pp.737-740

Publication Date: 2015/03/01

Publicized: 2014/11/21

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2014EDL8140

Type of Manuscript: LETTER

Category: Image Recognition, Computer Vision

Authors

Jong-Seung PARK
Hanbat National University
Seung-Ho LEE
Hanbat National University

Keyword

machine vision, mura detection, mura mask, mask filtering

Cite this

Copy

Jong-Seung PARK, Seung-Ho LEE, "Automatic Mura Detection for Display Film Using Mask Filtering in Wavelet Transform" in IEICE TRANSACTIONS on Information, vol. E98-D, no. 3, pp. 737-740, March 2015, doi: 10.1587/transinf.2014EDL8140.
Abstract: In this letter, we present a method for automatic mura detection for display film using the efficient decision of cut-off frequency with DCT and mask filtering with wavelet transform. First, the background image including reflected light is estimated using DCT with adaptive cut-off frequency, and DWT is applied to background-removed images for generating mura mask. Then, a mura mask is generated by separating low-frequency noise in the approximation coefficients. Lastly, mura is detected by applying mura mask filtering to the detail coefficients. According to the comparison by Semu index, the results from the proposed method are superior to those from the existing methods. This indicates that the proposed method is high in reliability.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.2014EDL8140/_p

Copy

@ARTICLE{e98-d_3_737,
author={Jong-Seung PARK, Seung-Ho LEE, },
journal={IEICE TRANSACTIONS on Information},
title={Automatic Mura Detection for Display Film Using Mask Filtering in Wavelet Transform},
year={2015},
volume={E98-D},
number={3},
pages={737-740},
abstract={In this letter, we present a method for automatic mura detection for display film using the efficient decision of cut-off frequency with DCT and mask filtering with wavelet transform. First, the background image including reflected light is estimated using DCT with adaptive cut-off frequency, and DWT is applied to background-removed images for generating mura mask. Then, a mura mask is generated by separating low-frequency noise in the approximation coefficients. Lastly, mura is detected by applying mura mask filtering to the detail coefficients. According to the comparison by Semu index, the results from the proposed method are superior to those from the existing methods. This indicates that the proposed method is high in reliability.},
keywords={},
doi={10.1587/transinf.2014EDL8140},
ISSN={1745-1361},
month={March},}

Copy

TY - JOUR
TI - Automatic Mura Detection for Display Film Using Mask Filtering in Wavelet Transform
T2 - IEICE TRANSACTIONS on Information
SP - 737
EP - 740
AU - Jong-Seung PARK
AU - Seung-Ho LEE
PY - 2015
DO - 10.1587/transinf.2014EDL8140
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E98-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2015
AB - In this letter, we present a method for automatic mura detection for display film using the efficient decision of cut-off frequency with DCT and mask filtering with wavelet transform. First, the background image including reflected light is estimated using DCT with adaptive cut-off frequency, and DWT is applied to background-removed images for generating mura mask. Then, a mura mask is generated by separating low-frequency noise in the approximation coefficients. Lastly, mura is detected by applying mura mask filtering to the detail coefficients. According to the comparison by Semu index, the results from the proposed method are superior to those from the existing methods. This indicates that the proposed method is high in reliability.
ER -