以關鍵點為基礎的印刷電路板自動元件佈局檢測系統實現之研究

This project aims to develop novel automated computer vision algorithms and systems for component replacement inspection for Printed Circuit Boards (PCBs). The proposed algorithms are able to identify locations as well as sizes of different components. They are object detection algorithms based on keypoints of the target components. The algorithms can be implemented as neural networks consisting of two portions: frontend networks and backend networks. The frontend networks are used for the feature extractions of input images. The backend networks are adopted for producing component inspection results. Each component class can have its own frontend and backend networks to achieve high detection accuracy. Furthermore, different component classes can share the same frontend networks to reduce the computation time for the inference of the networks. The proposed algorithm has been deployed in an Internet of Things (IoT) system on for the inspection of Printed Circuit Boards (PCBs) of GPU card devices. Because the proposed algorithm has the advantages of the simplicity for training data collection and high accuracy for defect detection for online inspection, it is observed that the proposed algorithm is an effective alternative for the automated inspection in smart factory with growing demand for product quality and diversification.