PCB INSPECTION SYSTEM

The AI-Based PCB Inspection and Status-Indication System is designed to provide an automated and low-cost approach for inspecting Printed Circuit Boards (PCBs) using computer vision, image processing, and Artificial Intelligence/Machine Learning techniques. Manual PCB inspection requires continuous visual checking and may be time-consuming and prone to human error. To address these limitations, the proposed system uses a camera to capture PCB images and processes them using Python-based image processing techniques. The system is divided into two major inspection modules: bare PCB inspection and assembled PCB inspection. In the bare PCB inspection module, the captured image is processed to analyze copper tracks and conductive paths. Image preprocessing techniques such as grayscale conversion, filtering, thresholding, edge detection, and morphological operations are used to obtain useful information from the PCB image. The system aims to identify defects such as track cuts, open traces, short circuits, and missing conductive paths by comparing the observed PCB pattern with the expected pattern. Machine learning and lightweight deep-learning techniques can then be used to classify the inspected PCB condition. The second module focuses on assembled PCB inspection. It checks important conditions such as the power-supply section and LED indicator. Visual information from the camera can be combined with electrical measurements to determine whether the assembled PCB satisfies the required conditions. After completing the inspection, the system generates a PASS or FAIL decision. The result can be communicated to a microcontroller through serial communication and indicated using a Green LED for PASS and a Red LED for FAIL, with an optional buzzer for fault indication.