Detection of Local Mura Defects in TFT-LCD Using Machine Vision

Authors:
Xin Bi;Han Ding
Affiliations:
Robotics Institute, School of Mechanical Engineering, Shanghai Jiaotong University, Shanghai, China 200240;Robotics Institute, School of Mechanical Engineering, Shanghai Jiaotong University, Shanghai, China 200240
Venue:
ICIRA '08 Proceedings of the First International Conference on Intelligent Robotics and Applications: Part I
Year:
2008

Citing 3
Cited 0

Multichannel Texture Analysis Using Localized Spatial Filters

IEEE Transactions on Pattern Analysis and Machine Intelligence
Unsupervised texture segmentation using Gabor filters

Pattern Recognition
Face Recognition Using Independent Gabor Wavelet Features

AVBPA '01 Proceedings of the Third International Conference on Audio- and Video-Based Biometric Person Authentication

Quantified Score

Hi-index	0.00

Visualization

Abstract

Machine vision is widely used in the field of defect inspection. Mura is a typical defect of LCD panel, appearing as local lightness variation with low contrast and blurry contour, so it is hard to be inspected with traditional thresholding or edge detection methods. This paper presents a machine vision Mura inspection method based on real Gabor filter. By selecting appropriate number of filtering scale and orientation, a set of real Gabor filter are formed and applied to the LCD images with defects. Then, through images fusion, all the sub-images from different channels are fused together and as a result, the global structurally textured backgrounds are eliminated and the local defects are preserved. As expected, the final binary images show the defects out. Experiments show that this method is suitable to the inspection of many types of Mura. Furthermore, it is insensitive to the rotation of image.