A Novel Multicategory Defect Detection Method Based on the Convolutional Neural Network Method for TFT-LCD Panels
Open Access
- 16 February 2022
- journal article
- research article
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2022, 1-14
Abstract
Defects on thin film transistor liquid crystal display (TFT-LCD) panel could be divided into either macro- or microdefects, depending on if they are easy to be detected by the naked eye or not. There have been abundant studies discussing the identification of macrodefects but very few on microones. This study proposed a multicategory classification model using a convolutional neural network model to work with automatic optical inspection (AOI) for identifying defective pixels on the TFT-LCD panel. Since the number of nondefective pixels outnumbered the defective ones, there exists a very serious class-imbalanced problem. To deal with that, this study designed a special training strategy that worked with data augmentation to increase the effectiveness of the proposed model. Actual panel images provided by a mobile manufacturer in Taiwan are used to demonstrate the efficiency and effectiveness of the proposed approach. After validation, the model constructed by this study had 98.9% total prediction accuracy and excellent specificity and sensitivity. The model could finish the detection and classification process automatically to replace the human inspection.Keywords
Funding Information
- Ministry of Science and Technology, Taiwan (MOST 110-2221-E-A49-120, MOST 110-2410-H-145-001)
This publication has 46 references indexed in Scilit:
- Landslide susceptibility assesssment in the Uttarakhand area (India) using GIS: a comparison study of prediction capability of naïve bayes, multilayer perceptron neural networks, and functional trees methodsTheoretical and Applied Climatology, 2015
- Data Augmentation for Deep Neural Network Acoustic ModelingIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2015
- Fuzzy Restricted Boltzmann Machine for the Enhancement of Deep LearningIEEE Transactions on Fuzzy Systems, 2015
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- Human photoreceptor topographyJournal of Comparative Neurology, 1990
- Backpropagation Applied to Handwritten Zip Code RecognitionNeural Computation, 1989
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989
- The Calculation of Posterior Distributions by Data AugmentationJournal of the American Statistical Association, 1987
- The perceptron: A probabilistic model for information storage and organization in the brain.Psychological Review, 1958