Automatic and early Detection of defects on Printed Circuits Bords (PCBs)

Abstract

Printed Circuit Boards (PCBs) are fundamental in electronic devices, connecting various parts to form functional circuits. Inspecting these boards for defects is crucial for ensuring their performance and reliability. This thesis concerned with the development of a Visual Inspection System for PCBs using advanced image processing and deep learning (DL) techniques. The system explores high-resolution images of PCBs. These images are then analyzed using pattern recognition, edge detection, and machine learning algorithms to detect defects. The main focus is on leveraging pre-trained deep learning models, particularly YOLO (You Only Look Once), for automatic and early defect detection