Defect Classification Using Machine Learning Techniques for Flat Display Panels

Abstract:

Defect classification for a flat display panel (FDP) is the crucial process that identifies and classifies defects automatically during the final step of its manufacturing process. It plays an important role since it prevents possible malfunction by inspecting defects timely and reduces time for identifying inferior products. In this paper, we propose the defect classification methods for FDP using various machine learning techniques and provide the comparison among them for practical use in production environment. First, we identify defects through Gaussian filter and threshold technique. Then, those defects are classified into different types based on geometric characteristics of them using four machine learning techniques that are widely used. The experimental results using training and test sets of FDP images show considerable effectiveness in classifying defect types. We also believe that the comparison result might be quite useful when engineers determine methods for defect classification during FDP manufacturing.

• Periodical: Applied Mechanics and Materials (Volumes 365-366)
• Pages: 720-724
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.365-366.720
• Online since: August 2013
• Authors: Du Hyung Cho, Seok Lyong Lee
• Keywords: Computer Vision, Defect Classification, Flat Display Panel, Image Analysis, Machine Learning Technique

References

[1] C.H. Noh, S.L. Lee, D.H. Kim, C.W. Chung and S.H. Kim, An effective and efficient defect inspection system for TFT-LCD polarised films using adaptive thresholds and shape-based image analyses, I J Prod. Res. 48, 17 (2010) 5115-5135.

DOI: 10.1080/00207540903117899

[2] D.M. Tsai, S.T. Chuang and Y.H. Tseng, One-dimensional-based automatic defect inspection of multiple patterned TFT-LCD panels using Fourier image reconstruction, I J Prod. Res. 45, 6 (2007) 1297-1321.

DOI: 10.1080/00207540600622464

[3] Y.G. Yoon, S.L. Lee, C.W. Chung and S.H. Kim: An effective defect inspection system for polarized film images using image segmentation and template matching techniques, Comp. & Ind. Eng. 55 (2008) 567-583.

DOI: 10.1016/j.cie.2008.01.015

[4] S.B. Kang, J.H. Lee, K.Y. Song and H.J. Pahk, Automatic defect classification of TFT-LCD panels using machine learning, Proc. of IEEE International Symposium on Industrial Electronics, (2009) 2175 - 2177.

DOI: 10.1109/isie.2009.5213760

[5] D. H Cho and S. L Lee: Defect Identification and Classification for Plasma Display Panels, Adv. Mat. Res., 694-697 (2013) 1197-1201.

DOI: 10.4028/www.scientific.net/amr.694-697.1197

[6] A. Yousefian, J. Liu and H. Lee, Automatic Inspection of TFT-LCD Glass Substrates Using Optimized Support Vector Machines, Proc. of 8th IFAC Symp. on Ad. Control of Chemical Processes, Singapore, July 10-13, (2012).

DOI: 10.3182/20120710-4-sg-2026.00054

[7] D.C. Tseng, I.L. Chung, P.L. Tsai and C.M. Chou, Defect Classificationfor LCD Color Filters Using Neural-Network Decision Tree Classifier, I J Innovative Computing, Information and Control, 7, 7 (2011) 3695-3707.

[8] M. S. Nixon and A. S. Aguado, Feature Extraction and Image Processing, Academic Press, (2008).

[9] N. A. Otsu, IEEE Tr. System Man and Cybernetics, 9, 62 (1979).

[10] D. H Cho and S.L. Lee: Efficient Data Association for Multiple Vehicles Tracking, App. Mech. and Mat., 263-266 (2013) 2426-2431.

DOI: 10.4028/www.scientific.net/amm.263-266.2426

[11] C. Cortes and V. Vapnik, Support-Vector Networks Machine Learning, (1995).

[12] N. Cristianini and J.S. Taylor, Introduction to Support Vector Machines, Cambridge Univ. Press, (2000).

[13] J. Han and M. Kamber, Data mining – Concepts and Techniques, Morgan Kaufmann Pub., (2006).