AI-BASED PCB DEFECT DETECTION AND REAL-TIME NOTIFICATION SYSTEM USING PYTHON

Abstract

Printed Circuit Boards (PCBs) are the fundamental building blocks of modern electronic devices, providing electrical connectivity and mechanical support for electronic components. Defects occurring during PCB manufacturing, such as missing holes, open circuits, short circuits, spurious copper, mouse bites, scratches, and missing components, can significantly affect product quality, reliability, and operational safety. Conventional PCB inspection methods primarily rely on manual visual inspection or traditional image processing techniques, which are often timeconsuming, labour-intensive, and prone to human error, especially in high-volume manufacturing environments. Recent advancements in Artificial Intelligence (AI), Deep Learning, Computer Vision, Convolutional Neural Networks (CNNs), Python, and OpenCV have enabled the development of intelligent automated inspection systems capable of detecting PCB defects with high accuracy and speed. This project presents an AI-Based PCB Defect Detection and RealTime Notification System Using Python. The proposed framework integrates a high-resolution camera, OpenCV image preprocessing, CNN-based defect detection model, Python processing environment, real-time notification module, database management system, and graphical user interface into a unified automated inspection platform. Initially, PCB images are captured using a camera and preprocessed through resizing, normalization, noise removal, and image enhancement techniques. The processed images are then supplied to the trained CNN model, which accurately identifies various PCB defects and classifies them into predefined defect categories. Whenever a defective PCB is detected, the system immediately generates a real-time notification, stores inspection results in the database, and displays defect information through the monitoring interface for quality engineers. Experimental evaluation demonstrates high defect detection accuracy, rapid processing speed, low false detection rate, reliable real-time notification, and stable system performance under different PCB inspection conditions. The proposed intelligent inspection framework significantly improves manufacturing quality, reduces inspection time, minimizes production losses, enhances product reliability, and provides an efficient solution for nextgeneration smart electronic manufacturing and Industry 4.0 applications. Keywords: Artificial Intelligence, PCB Defect Detection, Deep Learning, Convolutional Neural Network, Computer Vision, Python, OpenCV, Real-Time Notification, Automated Optical Inspection, Smart Manufacturing.