Detection of Conductive Particles in TFT-LCD Circuit Using Generative Adversarial Networks

Abstract

The inspection of conductive particles is a crucial step in the Thin Film Transistor Liquid Crystal Display (TFT-LCD) circuit detection process since only high-quality deformed particles have the conductive effect in the circuit. The main task of detecting conduction particles is to locate and count the valid particles accurately, which is a high challenge due to various difficulties such as the uneven illumination, different sizes to aggregation and overlap between particles, etc. Traditional detection algorithms need to manually set a large number of artificial thresholds, which limits their adaptability. As a result, effective automatic detection of conductive particles is strongly motived in industry. In this paper, a novel particle detection algorithm based on generative adversarial networks (GAN) is proposed for TFT-LCD circuit inspection system. The backbone architecture of the generator is based on a compact end-to-end neural network with multi-scale convolution blocks for well utilizing the multiscale spatial features. And the discriminator is designed to detect and correct high-order inconsistencies for real-fake images. Moreover, Coarse to Fine training strategy and Loss functions Coordination strategy are further proposed to improve the detection quality. The experiments on the real dataset demonstrate the effectiveness of the proposed methods for the detection of valid conductive particles compared to the state-of-the-art methods.

A Novel Attention-Based Multi-Modal Modeling Technique on Mixed Type Data for Improving TFT-LCD Repair Process

“…It is very helpful to reduce data labeling cost (human and time resource) and improve the generalization ability of AOI models. Y. Wang et al [25] proposed a novel particle detection algorithm based on GAN architecture with U-Net like multi-scale lightweight generator backbone and achieve real time inspection in TFT-LCD manufacturing. Lee et al [7] proposed an automatic defect repair algorithm for LCD repair machine.…”

Optimized Replication of ADC-Based Particle Counting Algorithm with Reconfigurable Multi-Variables in Pseudo-Supervised Digital Twining of Reference Dust Sensor Systems

“…Dust-sensing devices digitize and provide dust concentration information in the air. The use of a digital twin of dust concentration is important in minimizing the occurrence of defects in ultra-fine processes in the industrial field [ 16 ], and in the case of buildings, it is used for periodic internal air circulation [ 17 , 18 ]. The importance of digital twins in the continuous management and conservation of energy consumption, particularly in relation to the heating, ventilation, and air conditioning systems of buildings, is consistently increasing [ 19 ].…”

Runtime Tracking-Based Replication of On-Chip Embedded Software Using Transfer Function Learning for Dust Particle Sensing Systems

“…The measurement of PM is also important in the product manufacturing process in the industry because it causes several defects. For example, in the manufacturing process of thin film transistor-liquid crystal displays (TFT-LCDs), the TFT-LCD panel defects may occur owing to the mixing of particles [7]. In this case, measuring the concentration of PM is important to reduce the defect rate.…”