This repository contains source code, program, and experimental results of the paper entitled 'A YOLO-based Real-time Packaging Defect Detection System'
Abstract
Managing the quality of products is the primary concern in manufacturing production to benefit the business. There are numerous different approaches for improving the product quality management in manufacturing. Each approach has certain advantages and limitations, and the common goal is to bring the best efficiency in managing product quality in production lines. In this paper, we introduce our approach to creating a real-time packaging defect detection system based on deep learning techniques intending to automatically recognize defective packaged products in industrial quality control of packages. To be more precise, we present a flexible real-time defect detection system in helping classify product quality automatically based on the YOLO (You only look once) algorithm. The system can be easily integrated into factories, quickly deployed, and installed in production lines, helping to optimize efficiency and save operating costs.
**The system architecture**
**Training results**
**Training results**
**The system GUI**
If you need any additional information, don't hesitate to contact me at thuhuyen (at) kyonggi dot ac dot kr