Automatic target defect identification for TFT-LCD array process inspection using kernel FCM-based fuzzy SVDD ensemble

Liu, Yi-Hung; Lin, Szu-Hsien; Hsueh, Yi-Ling; Lee, Ming-Jiu

doi:10.1016/j.eswa.2007.12.015

Cited by 64 publications

(36 citation statements)

References 36 publications

(46 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, if macro defects are inspected in the fabrication process, it will be helpful in increasing the production yield and decreasing the production cost. Recently, for this reason, there has been some research on defect inspection in the TFT fabrication process [9]. However, Liu et al only focused on the inspection of micro defects because photomask misalignments can cause micro defects.…”

Section: Introductionmentioning

confidence: 99%

Automatic inspection method for macro defects in TFT-LCD color filter fabrication process

Son

2009

IEICE Electron. Express

View full text Add to dashboard Cite

Defect inspection of thin film transistor liquid crystal displays (TFT-LCDs) is divided into two steps: detection and judgment. This letter proposes an automatic detection and judgment method for macro defects in the TFT-LCD color filter (CF) fabrication process using the diffraction pattern shift and chromaticity, respectively. The proposed method is verified via experiments using sampled CF glasses with macro defects, which were judged as PASS (no defect) in the CF fabrication process by a human operator who inspects CF glasses using conventional inspection systems, but were rejected in the module process. Seventeen rejected glasses were used in the experiments. All macro defects, including non-uniformity under 300Å, were detected and are judged as REJECT (defect) using the proposed method.

show abstract

Section: Introductionmentioning

confidence: 99%

Automatic inspection method for macro defects in TFT-LCD color filter fabrication process

Son

2009

IEICE Electron. Express

View full text Add to dashboard Cite

show abstract

“…Therefore, neural networks have limited applications in the mura inspection of thin film transistor-liquid crystal displays (TFT-LCDs) [14,15] and in the relatively simple patterns of light emitting diodes (LEDs) [16,17]. In particular, the support vector data description (SVDD) method using a fuzzy penalty function has been proposed to inspect defects in gate electrodes [15,18].…”

Section: Introductionmentioning

confidence: 99%

“…In approaches using neural networks and statistical methods [14][15][16][17][18][19][20], it is difficult to discriminate the defective area with periodic backgrounds. Therefore, neural networks have limited applications in the mura inspection of thin film transistor-liquid crystal displays (TFT-LCDs) [14,15] and in the relatively simple patterns of light emitting diodes (LEDs) [16,17].…”

Section: Introductionmentioning

confidence: 99%

“…Most existing approaches for defect inspection in periodic patterns can be divided into three main classes: (1) template matching [1][2][3][4][5][6][7][8][9][10][11][12][13]; (2) neural networks [14][15][16][17][18][19][20]; and (3) filter approaches [21][22][23][24][25][26][27][28][29][30][31][32][33]. A few other studies have reported approaches other than the abovementioned [34].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Defect detection in periodic patterns using a multi-band-pass filter

Tsai

Perng

2012

Machine Vision and Applications

View full text Add to dashboard Cite

This study presents a rapid and reliable technique for the inspection of defects in a two-dimensional periodic image using a multi-band-pass filter. More importantly, the blurring effect of the resultant defect images is significantly reduced, thereby resulting in a more precise estimation of the size of defects when compared with methods that use low-pass filtering. As a filter-based approach, the present technique does not require an alignment procedure. In addition, computational time is reduced by implementing multiband-pass filters with convolution masks when the filters are operated in the spatial domain. Further, this approach involves mostly addition operations with very few multiplications; hence, computational time is significantly reduced when compared with those for existing approaches. The efficiency and effectiveness of the proposed multi-band-pass filter is verified through examples. It is observed that there is a significant reduction in blurring effects, leakage effects, and computational effort. It is noteworthy that though the proposed approach is presented as a two-dimensional filtering problem, it can be reduced to a one-dimensional filtering problem under the assumption that the misorientation angle of the inspected periodic pattern is negligibly small.

show abstract

“…SVDD can get a more flexible boundary to adapt irregularly shaped target datasets, which is able to be effectively applied to the field of anomaly detection. [21][22][23][24] However, in the training phase, SVDD is required to solve the quadratic programming problem with the strength of calculation and obtain the decision boundary of target data. If the number of training samples is M, then its computational complexity will be up to O(M 3 ).…”

Section: Introductionmentioning

confidence: 99%

A new approach of anomaly detection in wireless sensor networks using support vector data description

Zhu

et al. 2017

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

Anomaly detection is an important challenge in wireless sensor networks for some applications, which require efficient, accurate, and timely data analysis to facilitate critical decision making and situation awareness. Support vector data description is well applied to anomaly detection using a very attractive kernel method. However, it has a high computational complexity since the standard version of support vector data description needs to solve quadratic programming problem. In this article, an improved method on the basis of support vector data description is proposed, which reduces the computational complexity and is used for anomaly detection in energy-constraint wireless sensor networks. The main idea is to improve the computational complexity from the training stage and the decision-making stage. First, the strategy of training sample reduction is used to cut back the number of samples and then the sequential minimal optimization algorithm based on the second-order approximation is implemented on the sample set to achieve the goal of reducing the training time. Second, through the analysis of the decision function, the pre-image in the original space corresponding to the center of hyper-sphere in kernel feature space can be obtained. The decision complexity is reduced from O(l) to O(1) using the pre-image. Eventually, the experimental results on several benchmark datasets and real wireless sensor networks datasets demonstrate that the proposed method can not only guarantee detection accuracy but also reduce time complexity.

show abstract

Automatic target defect identification for TFT-LCD array process inspection using kernel FCM-based fuzzy SVDD ensemble

Cited by 64 publications

References 36 publications

Automatic inspection method for macro defects in TFT-LCD color filter fabrication process

Automatic inspection method for macro defects in TFT-LCD color filter fabrication process

Defect detection in periodic patterns using a multi-band-pass filter

A new approach of anomaly detection in wireless sensor networks using support vector data description

Contact Info

Product

Resources

About