A Review of TFT-LCD Panel Defect Detection Methods

Abstract:

TFT-LCD panel defect detection has been one of the difficulties in this field because of fuzzy defect boundary, low contrast between defects and background, and low detection speed. The structure of TFT-LCD panels and classification are introduced. Through the analysis of panel defect features, current detection methods for the TFT-LCD panel defects are reviewed. The key technologies of feature extraction and defect classification are analyzed in the defect image recognition of TFT-LCD panel. Meanwhile the methods of fuzzy boundary defect segmentation, image subtraction and image filtering are also discussed. Finally, the characteristics and advantages of these detection methods are concluded, and several key issues for the TFT-LCD defect detection have been proposed for future development.

• Periodical: Advanced Materials Research (Volumes 734-737)
• Pages: 2898-2902
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.734-737.2898
• Online since: August 2013
• Authors: Chuan Xia Jian, Jian Gao, Xin Chen
• Keywords: Detect Defection, Image Processing, Image Recognition, TFT-LCD

References

[1] Tsai D M, Hung C Y. International journal of production research, 2005,43 (21):4589-4607.

[2] Tsai D M, Chuang S T, Tseng Y H. International journal of production research, 2007, 45 (6): 1297-1321.

[3] Bi X. Study on the methods of machine vision inspection for the mura defect of TFT-LCD process [D]. Shanghai：Shanghai Jiaotong University, 2008. (In Chinese)

[4] Zhang Y. Research on Mura inspection technology of TFT-LCD based on machine vision [D]. Harbin：Harbin Institute of Technology, 2006. (In Chinese)

[5] Yi H L, Szu H L, Yi L H, et al. Expert Systems with Applications, 2009,36 (2):1978-1998.

[6] Yi H L, Yu K H, Ming J L. Measurement Science and Technology, 2008, 19(9):1-16.

[7] Yi H L, Yan C L, Yen Z C. Expert Systems with Applications, 2011,38 (5):6222-6231.

[8] Yi H L, Yan C L. Reducing the run-time complexity of support vector data descriptions [C]// Int. Joint Conf. on Neural Networks, Atlanta, USA, 2009: 1863 - 1870.

DOI: 10.1109/ijcnn.2009.5179024

[9] Yi H L, Yan C L ,Yen J C. Neural Networks, 2010,21(8): 1296 - 1313.

[10] Li F C, Chao T S, Meng H C. Electronics Packaging Manufacturing, 2009, 32(1):1-8.

[11] Chi H Y, Ful C W. An image enhancement technique in inspecting visual defects of polarizers in TFT-LCD industry [C]// Int. Conf. on Computer Modeling and Simulation, Macau, China, 2009: 257 - 261.

DOI: 10.1109/iccms.2009.73

[12] Shin M C, Du M T. Image and Vision Computing, 2008, 26(2): 187-200.

[13] Shin M C, Du M T. Pattern Recognition, 2010, 43(5): 1917-1931.

[14] Shin M C, Du M T, Yan H T, et al. Defect detection in low-contrast glass substrates using anisotropic diffusion [C]// 20th Int. Conf. on Pattern Recognition, Hong Kong, China, 2006: 654 - 657.

DOI: 10.1109/icpr.2006.427

[15] Jae Y L, Suk I Y. IEICE Transactions on Information and Systems, 2004, E87-D (10): 2371-2378.

[16] No K P, Suk I Y. Displays, 2009, 30 (1): 1-16.

[17] Wang Z Y, Ma L. Implementation of region-mura detection based on recursive polynomial-surface fitting algorithm [C]// Second Asia Int. Sym. Mechatronics, Hong Kong, China, 2006:1–6.

[18] Chen F C, Fang L T, Lee L, et al. LOG filter based inspection of cluster mura and vertical-band mura on liquid crystal displays [C]// Proc. of SPIE, San Jose, USA, 2005,5679: 257-265.

DOI: 10.1117/12.586688