Design of Detection System Based on Digital LCD Touch Screen

Authors

  • Jiahao Cai Jinshan College of Fujian Agriculture and Forestry University, Fuzhou, Fujian, 350002

Keywords:

LCD Touchscreen, Automated Optical Inspection (AOI), Digital Detection System, Image Processing, Smart Manufacturing, Quality Control, Data Tracing, Flexible Production

Abstract

Traditional Liquid Crystal Display (LCD) touchscreen manufacturing processes are often hampered by testing systems characterized by low levels of automation. These legacy systems suffer from significant limitations, including an inability to seamlessly exchange test data with other devices in the production line and a lack of flexibility to accommodate products with multiple specifications. This data siloing and inflexibility create bottlenecks, impede statistical process control, and hinder the transition towards smart manufacturing. In response to these challenges, this paper presents the design and development of a novel, digitized detection system specifically for LCD touchscreens. The core of the proposed system utilizes an industrial image acquisition card to capture high-fidelity digital images of the unit under test. Subsequently, a suite of advanced image processing algorithms is applied. Key to its operation is the capability to filter and analyze specific regions of interest (ROI) based on configurable area thresholds, enabling precise and automated screen inspection for defects such as dead pixels, scratches, and Mura effects. The system's architecture is designed for versatility, allowing it to be easily reconfigured to test different specifications of LCD touchscreens and associated Flexible Printed Circuit (FPC) boards. Its functionality comprehensively covers critical assembly stages, including the inspection of plug-in components, the quality of hot-pressing (e.g., for FPC attachment), and continuity or wiring tests. The implementation of this system facilitates fine-grained management of the production workflow, empowers intelligent defect recognition, and establishes complete data tracing from raw materials to finished goods. Empirical results from deployment demonstrate tangible benefits, notably a significant reduction in manual labor requirements, a marked improvement in testing efficiency and throughput, and a substantial elevation of the overall digitization level within the production environment. This research provides a practical and scalable solution for modernizing quality control in display manufacturing.

References

Chen, Yang, et al. "SyntheClean: Enhancing Large-Scale Multimodal Models via Adaptive Data Synthesis and Cleaning." 2025 5th International Conference on Artificial Intelligence and Industrial Technology Applications (AIITA). IEEE, 2025.

Jiang, Gaozhe, et al. "A Knowledge-Enhanced Multi-Task Learning Model for Domain-Specific Question Answering." 2025 7th International Conference on Information Science, Electrical and Automation Engineering (ISEAE). IEEE, 2025.

Zhuo, Jiayang, et al. "An Intelligent-Aware Transformer with Domain Adaptation and Contextual Reasoning for Question Answering." 2025 IEEE 6th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT). IEEE, 2025.

Zhang, Hanlu, et al. "Dynamic Attention-Guided Video Generation from Text with Multi-Scale Synthesis and LoRA Optimization." 2025 4th International Symposium on Computer Applications and Information Technology (ISCAIT). IEEE, 2025.

Zhao, Shihao, et al. "KET-GPT: A Modular Framework for Precision Knowledge Updates in Pretrained Language Models." 2025 IEEE 6th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT). IEEE, 2025.

Shih, Kowei, et al. "DST-GFN: A Dual-Stage Transformer Network with Gated Fusion for Pairwise User Preference Prediction in Dialogue Systems." 2025 8th International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE). IEEE, 2025.

Li, Xuan, et al. "MLIF-Net: Multimodal Fusion of Vision Transformers and Large Language Models for AI Image Detection." 2025 8th International Conference on Advanced Algorithms and Control Engineering (ICAACE). IEEE, 2025.

Xie, Minhui, and Shujian Chen. "CoreViz: Context-Aware Reasoning and Visualization Engine for Business Intelligence Dashboards." Authorea Preprints (2025).

Zhu, Bingxin. "TraceLM: Temporal Root-Cause Analysis with Contextual Embedding Language Models." (2025).

Zhang, Yuhan. "SafeServe: Scalable Tooling for Release Safety and Push Testing in Multi-App Monetization Platforms." (2025).

Hu, Xiao. "UnrealAdBlend: Immersive 3D Ad Content Creation via Game Engine Pipelines." (2025).

Qin, Haoshen, et al. "Optimizing deep learning models to combat amyotrophic lateral sclerosis (ALS) disease progression." Digital health 11 (2025): 20552076251349719.

Ding, C.; Wu, C. Self-Supervised Learning for Biomedical Signal Processing: A Systematic Review on ECG and PPG Signals. medRxiv 2024.

D. Restrepo, C. Wu, S.A. Cajas, L.F. Nakayama, L.A. Celi, D.M. López. Multimodal deep learning for low-resource settings: A vector embedding alignment approach for healthcare applications. (2024), 10.1101/2024.06.03.24308401

Zeng, Yuan, et al. "Education investment, social security, and household financial market participation." Finance Research Letters 77 (2025): 107124.

Wang, Hao. "Joint Training of Propensity Model and Prediction Model via Targeted Learning for Recommendation on Data Missing Not at Random." AAAI 2025 Workshop on Artificial Intelligence with Causal Techniques. 2025.

Downloads

Published

2025-10-30

How to Cite

Cai, J. (2025). Design of Detection System Based on Digital LCD Touch Screen. International Journal of Advance in Applied Science Research, 4(7), 6–10. Retrieved from https://h-tsp.com/index.php/ijaasr/article/view/111

Issue

Section

Articles