Application research of machine vision in LCD panel flaw detection

Chaofan Xie; Xuan Hong Jin; Shuguang Dai

doi:10.1117/12.828824

20 May 2009 Application research of machine vision in LCD panel flaw detection

Chaofan Xie, Xuan Hong Jin, Shuguang Dai

Proceedings Volume 7283, 4th International Symposium on Advanced Optical Manufacturing and Testing Technologies: Optical Test and Measurement Technology and Equipment; 72834E (2009) https://doi.org/10.1117/12.828824
Event: AOMATT 2008 - 4th International Symposium on Advanced Optical Manufacturing, 2008, Chengdu, Chengdu, China

Abstract

This paper introduced the machine vision technology into the LCD (Liquid Crystal Display) panel flaw inspection system, in order to detect flaws accurately and quickly. There are two major kinds of flaws in LCD panel: white dots and black dots. Image segmentation can be used to inspect flaws, and a general method is applying a threshold to the whole image. But because of illumination unconformity, the acquired image has varied pixel brightness, and some pixels in the border even have a lower brightness than the black dots. So gradient thresholding based on local pixels is adopted, but because the image sensor and the LCD panel both have a array frame, there exists moiré fringes in the image. Thus, a novel method of gradient thresholding based on moiré fringes is put forward. And noises handling is discussed at end. Experimental results show that the proposed novel method is effective

Citation Download Citation

Chaofan Xie, Xuan Hong Jin, and Shuguang Dai "Application research of machine vision in LCD panel flaw detection", Proc. SPIE 7283, 4th International Symposium on Advanced Optical Manufacturing and Testing Technologies: Optical Test and Measurement Technology and Equipment, 72834E (20 May 2009); https://doi.org/10.1117/12.828824

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available