Automatic defect inspection system of colour filters using Taguchi-based neural network

Abstract

A coloured filter is a critical part of an LCD panel, especially to present a high quality colour display. At present, the defect detection of colour filters is conducted by manual inspection in the final product stage. However, poor detection efficiency and subjective judgment of manual inspection undermine accuracy. Therefore, this study applied image processing technology and the neural network to detect surface defects of colour filters in order to prevent losses arising from incorrect detection, lower production costs, and effectively improve yield. A back-propagation neural network (BPNN) classifier was selected to train the features. The results showed that the proposed method can be successfully applied in defect detection of colour filters to reduce artificial detection errors. In addition, the Taguchi method was used with BPNN to save time searching optimal learning parameters by the trial and error method, which achieves faster convergence, smaller convergent errors and better recognition rate. The results proved that the root-mean-square error (RMSE) of the Taguchi-based BPNN at final convergence is 0.000254, and recognition rate reaches 94%. Therefore, the proposed method has good effects in detecting the micro defects of a colour filter panel.

Identification of species and geographical strains ofSitophilus oryzaeandSitophilus zeamaisusing the visible/near-infrared hyperspectral imaging technique

“…This study used a backpropagation neural network (BPNN) to develop identification models. BPNN is one of the most popular predictive tools at present and is widely used in various other fields . BPNN is an artificial neural network (ANN) with three or more layers.…”

“…BPNN is one of the most popular predictive tools at present and is widely used in various other fields. 24 -26 BPNN is an artificial neural network (ANN) with three or more layers. Sample data imported into the network were sent from the input layer and through the intermediate layer to obtain a response signal from the output layer.…”

Automated Inspection of Surface Defects Using Machine Vision

“…However, the study had similar limitations work in terms of the applicability and number of detected defects [12]. Kuo et al [13] used similar VBI System for defect detection in LCD filters including: fiber, particle, gel, and resist coating. The Defect feature including defect area, aspect ratio, squareness ratio and damage ratio are calculated and input to BPNN to classify the defects.…”

Computer-based management of interactive data transformation systems using Taguchi’s robust parameter design

“…The orthogonal array can be utilised in experiments which sometimes mix two equivalent parameters and sometimes mix parameters with different levels (Muñoz-Escalona and Maropoulos 2010). A loss function in the form of a signal-to-noise ratio is also used to measure the amount which characteristics deviate from their desired values (Kuo et al 2013). Firstly, the system design considers different levels of concepts and choices of technology.…”