Independent component analysis-based defect detection in patterned liquid crystal display surfaces

We present in this paper a framework for the automatic detection and localization of defects inside bridge decks. Using Ground-Penetrating Radar (GPR) raw scans, this framework is composed of a feature extraction algorithm using fractals to detect defective regions and a deconvolution algorithm using banded-independent component analysis (ICA) to reduce overlapping between reflections and to estimate the radar waves travel time and depth of defects. Results indicate that the defects' estimated horizontal location and depth falling within 2 cm (76.92% accuracy) and 1 cm (84.62% accuracy) from their actual values.

Download Full-text

An Independent Component Analysis Based Defect Detection for the OLED Display

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.605-607.724 ◽

2012 ◽

Vol 605-607 ◽

pp. 724-728 ◽

Cited By ~ 1

Author(s):

Zhi Liang Wang ◽

Jian Gao ◽

Chuan Xia Jian ◽

Yao Cong Liang ◽

Yu Cen

Keyword(s):

Independent Component Analysis ◽

Defect Detection ◽

Detection System ◽

Component Analysis ◽

Rapid Identification ◽

Independent Component ◽

Display Device ◽

Low Contrast ◽

Light Emitting ◽

Mixing Matrix

Organic Light Emitting Displays (OLED) is a new type of display device which has become increasingly attractive and popular. Due to the complex manufacturing process, various defects may exist on the OLED panel. These defects have the characteristics of fuzzy boundaries, irregular in shape, low contrast with background and they are mixed with the texture background increasing the difficulty of a rapid identification. In this paper, we proposed an approach to detect these defects based on the model of independent component analysis (ICA). The ICA model is applied to a perfect OLED image to determine the de-mixing matrix and its corresponding independent components (ICs). Through the choice of a proper ICi row vector, the new de-mixing matrix is generated which contains only uniform information and is used to reconstruct the OLED background image. The defect result can be obtained by the subtracting operation between the reconstructed background and the source images. The detection system is implemented in the Labview and the testing results show that the ICA based OLED defect detection method is feasible and effective.

Download Full-text

A Novel Method for Surface Defect Detection of Photovoltaic Module Based on Independent Component Analysis

Mathematical Problems in Engineering ◽

10.1155/2013/520568 ◽

2013 ◽

Vol 2013 ◽

pp. 1-8 ◽

Cited By ~ 4

Author(s):

Xuewu Zhang ◽

Hao Sun ◽

Yun Zhou ◽

Ji Xi ◽

Min Li

Keyword(s):

Independent Component Analysis ◽

Defect Detection ◽

Surface Defect ◽

Reconstruction Algorithm ◽

Component Analysis ◽

Training Image ◽

Independent Component ◽

Photovoltaic Module ◽

Surface Defect Detection ◽

Mixing Matrix

This paper proposed a new method for surface defect detection of photovoltaic module based on independent component analysis (ICA) reconstruction algorithm. Firstly, a faultless image is used as the training image. The demixing matrix and corresponding ICs are obtained by applying the ICA in the training image. Then we reorder the ICs according to the range values and reform the de-mixing matrix. Then the reformed de-mixing matrix is used to reconstruct the defect image. The resulting image can remove the background structures and enhance the local anomalies. Experimental results have shown that the proposed method can effectively detect the presence of defects in periodically patterned surfaces.

Download Full-text