Defect Detection in Printed Circuit Boards Using Semi-Supervised Learning

Printed Circuit Board (PCB) defect inspection is critical in electronics manufacturing, yet annotating large training sets is labor-intensive and costly. This paper proposes a semi-supervised PCB defect detection framework based on YOLOv5, which leverages a small labeled dataset and a larger pool of unlabeled images through an iterative self-training pipeline. A YOLOv5 detector is first trained on the limited labeled data, then used to generate pseudo-labels on unlabeled images; high-confidence detections are retained as defect annotations, and the model is retrained on the combination of labeled and pseudo-labeled data. This pseudo-labeling and retraining cycle is repeated for multiple iterations to progressively refine the detector. The approach is evaluated on a PCB defect dataset with 100 labeled and 1,000 unlabeled images, and shows significant gains over a fully supervised baseline. The proposed semi-supervised YOLOv5 achieves 91.6% mAP@0.5 with only 100 labeled images, outperforming both the baseline (87.0% mAP) and prior semi-supervised methods, while substantially improving recall and precision. The results demonstrate that the method effectively reduces annotation effort while maintaining high detection accuracy, providing a simple, confidence-thresholded self-training strategy for deploying PCB defect detectors under limited labeling resources. This work directly supports SDG 9 by enabling cost-efficient, high-accuracy AI-based PCB inspection that strengthens intelligent and sustainable manufacturing systems.

Printed circuit boards (PCBs) are primarily used to connect electronic components to each other. It is one of the most important stages in the manufacturing of electronic products. A small defect in the PCB can make the final product inoperable. Therefore, careful and meticulous defect detection steps are necessary and indispensable in the PCB manufacturing process. The detection methods can generally be divided into manual inspection and automatic optical inspection (AOI). The main disadvantage of manual detection is that the detection speed is too slow, resulting in a waste of human resources and costs. Thus, in order to speed up the production speed, AOI techniques have been adopted by many PCB manufacturers. Most current AOI mechanisms use traditional optical algorithms. These algorithms can easily lead to misjudgments due to different light and shadow changes caused by slight differences in PCB placement or solder amount so that qualified PCBs are judged as defective products, which is also the main reason for the high misjudgment rate of AOI detection. In order to effectively solve the problem of AOI misjudgment, manual re-judgment is currently the reinspection method adopted by most PCB manufacturers for defective products judged by AOI. Undoubtedly, the need for inspectors is another kind of labor cost. To reduce the labor cost. of manual re-judgement, an accurate and efficient PCB defect reinspection mechanism based on deep learning algorithm is proposed. This mechanism mainly establishes two detection models, which can classify the defects of the product. When both models have basic recognition capabilities, the two models are then combined into a main model to improve the accuracy of defect detection. In the study, the data provided by Lite-On Technology Co., Ltd. were implemented. To achieve the practical application value in the industry, this research not only considers the problem of detection accuracy, but also considers the problem of detection execution speed. Therefore, fewer parameters are used in the construction of the model. The research results show that the accuracy rate of defect detection is about 95%, and the recall rate is 94%. Compared with other detection modules, the execution speed is greatly improved. The detection time of each image is only 0.027 s, which fully meets the purpose of industrial practical application.

With the advancement of Industry 4.0, the need to integrate intelligent technologies into production processes has grown, aiming for greater automation, efficiency, and quality control. Aligned with this context, this project developed a supervisory system for solder quality inspection on printed circuit boards (PCBs) in the surface-mount technology (SMT) process, using artificial intelligence (AI). Currently, inspections performed by AOI (Automated Optical Inspection) machines generate data in multiple formats (HTML, TXT, and PDF), but their collection and analysis are manual. This makes the process slow, error-prone, and poorly integrated, hindering real-time decision-making. To overcome these limitations, an automated system was developed, including a RESTful API for module integration, a relational database for efficient data storage, a graphical interface with dashboards, and AI models for predictive analysis. The AI, based on Convolutional Neural Networks using Keras and TensorFlow, enables precise detection of solder defects, reducing the need for human intervention. The project followed a hybrid methodology, combining Scrum for agile software development and the Waterfall model for the sequential stages of hardware and research. The team was divided into hardware and software groups, with defined tasks for each phase of the schedule. The main phases included planning, SMT process mapping, system module development and integration, functional and performance testing, and user validation. The system was delivered validated, with formal acceptance from the client. The result is an intelligent solution that automates inspection in the SMT process, increases reliability, reduces failures, and promotes digital transformation in line with the principles of Industry 4.0.

Through the use of automatic inspection systems is possible to improve the Printed Circuits Board (PCB) manufacturing and reduce the fail rate in this process. In this paper an automatic inspection system for detecting small PCB defects is presented, the system uses a 2-D high precision laser sensor; this kind of laser sensor allows getting high precision measurements with an error of units of micrometers. The sensor is able to detect Surface-Mount Devices (SMD) onto PCB in order to perform a defect-detection process. The system uses an open, modular and scalable architecture for controlling a robotic motion in two axes, also a graphic application coded in Java for data processing and unify all the components is developed. Finally a judgment algorithm for defect-detection evaluation using binary matrices is added to the system. The aim of this system is that it can detect small PCB defects using a 2-D laser sensor and that is possible to implement it in a production line. Design, tests and results gotten are shown.

This paper presents inspection of Printed Circuit Boards (PCBs) based on normalized crosscorrelation. Correlation gives the similarity measure of images. In this paper, Normalized Cross-Correlation has been used to differentiate between a defective and defect free printed circuit board. Different PCBs have been inspected using normalized cross-correlation in this paper and further defected PCBs have been used for detection of all possible defects. Image subtraction(one of referential methods) is used for detection of defects of PCBs. And after detection of defects using image subtraction method, the wrong hole defects, missing conductors defects, etching defects, break lines have been classified.

Inspection of defects in the printed circuit boards (PCBs) has both safety and economic significance in the 4.0 industrial manufacturing. Nevertheless, it is still a challenging problem to be studied in-depth due to the complexity of the PCB layouts and the shrinking down tendency of the electronic component size. In this paper, a real-time automated supervision algorithm is proposed to test the PCBs quality among different scenarios. The density of the PCBs layout and the complexity on the surface are analyzed based on deep learning and image feature extraction algorithms. To be more detailed, the ORB feature and the Brute-force matching method are utilized to match perfectly the input images with the PCB templates. After transferring images by aiding the RANSAC algorithm, a hybrid method using modern computer vision algorithms is developed to segment defective areas on the PCBs surface. Then, by applying the enhanced Residual Network –50, the proposed algorithm can classify the groove defects on the surface mount technology electronic components which minimum size up to 1x3 mm. After the training process, the proposed system is capable to categorize various types of overproduced, recycled, and cloned PCBs. The speed of the quality testing operation maintains at a high level with an average precision rate up to 96.29 % in case of good brightness conditions. Finally, the computational experiments demonstrate that the proposed system based on deep learning can obtain superior results and it outperforms several existing works in terms of speed, precision, and robustness

Automated Optical Inspection (AOI) Systems are commonly used on Printed Circuit Boards (PCB) manufacturing. The use of this technology has been proven as highly efficient for process improvements and quality achievements. The correct extraction of the component for posterior analysis is a critical step of the AOI process. Nowadays, the Pattern Matching Algorithm is commonly used, although this algorithm requires extensive calculations and is time consuming. This paper will present an improved algorithm for the component localization process, with the capability of implementation in a parallel execution system.

Printed circuit board (PCB) defect detection is essential for ensuring the reliability of electronic manufacturing. Traditional automated optical inspection (AOI) methods rely on handcrafted features and rule-based heuristics, which often fail under complex defect patterns. Recent progress in deep learning, particularly the YOLO family of object detectors, has significantly improved industrial inspection. This paper presents a systematic benchmark of the YOLOv12 series, including five model scales (n, s, m, l, x), for PCB defect detection. All variants are trained and evaluated under unified protocols on a standard PCB dataset. Results show that YOLOv12l and YOLOv12x achieve the highest accuracy (mAP@0.5 ≈ 0.88 – 0.89), while YOLOv12n and YOLOv12s provide superior inference speed ( inference-only >300 FPS, end-to-end 6–8 FPS) at the expense of precision. YOLOv12m emerges as the most balanced variant, offering ~0.92 mAP@0.5 with real-time throughput. Error analysis using precision – recall curves and confusion matrices highlights challenges in fine-grained categories such as spur and mouse_bite. These findings provide practical guidelines for selecting YOLOv12 variants in PCB inspection, balancing accuracy and efficiency for diverse deployment scenarios.

Industry 4.0 is currently the goal of many factories, promoting manufacturing factories and sustainable operation. Automated Optical Inspection (AOI) is a part of automation. Products in the production line are usually inspected visually by operators. Due to human fatigue and inconsistent standards, product inspections still have defects. In this study, the sample component assembly printed circuit board (PCB), PCB provided by the company was tested for surface components. The types of defects on the surface of the PCB include missing parts, multiple parts, and wrong parts. At present, the company is still using visual inspection by operators, the PCB surface components are more complex. In order to reduce labor costs and save the development time required for different printed circuit boards. In the proposed method, we use digital image processing, positioning correction algorithm, and deep learning YOLO for identification, and use 450 images and 10500 components of the PCB samples. The result and contribution of this paper shows the total image recognition rate is 92% and the total component recognition rate reaches 99%, and they are effective. It could use on PCB for different light, different color backplanes, and different material numbers, and the detection compatibility reaches 98%.

Printed circuit boards (PCBs) are ubiquitous and essential electronic components. Tiny targets and high precision are the focus of PCB defect detection. This paper proposes an improved model focusing on tiny defect detection and model compression to achieve better performance in PCB defect detection. The improved model has a compact structure based on MobileNet v3 Small-CA and an image-cutting layer. Moreover, it applies an improved multi-scale fusion step with a location weighted mechanism to enhance representation performance. The proposed model outperforms state-of-the-art detection algorithms such as Faster R-CNN, EfficientDet, SSD, and YOLO v7, based on experimental results on a public synthetic PCB dataset. The proposed tiny object detection model has better performances on speed and detection accuracy, thereby benefitting the manufacturing industries associated with PCBs.

Automated Optical Inspection (AOI) systems are rapidly replacing slow and tedious manual inspections of Printed Circuit Boards (PCBs). In an AOI system, a minicamera traverses the PCB in a pre-defined travel path, snapping shots of all the PCB components or nodes, at pre-defined locations. The images are then processed and information about the different nodes is extracted and compared against ideal standards stored in the AOI system. This way, a flawed board is detected. Minimizing both the number of images required to scan all the PCB nodes, and the path through which the camera must travel to achieve this, will minimize the image acquisition time and the traveling time, and thus the overall time of inspection. This consequently both reduces costs and increases production rate. This work breaks down this problem into two sub-problems: The first is a clustering problem; the second a travelling salesman sequencing problem. In the clustering problem, it is required to divide all the nodes of a PCB into the minimum number of clusters. The cluster size is constrained by the given dimensions of the camera’s scope or Field of Vision (FOV). These dimensions determine the dimension of the inspection windows. It is thus required to find the minimum number of inspection windows that will scan all the nodes of a PCB, and their locations. Genetic algorithms are applied in a two-step approach with special operators suited for the problem. A continuous Genetic Algorithm (GA) is applied to find the optimum inspection window locations that cover one node and as many other nodes as possible. A discrete GA is then applied to eliminate redundant inspection windows leaving the minimum number of windows that cover all nodes throughout the PCB. In the second sub-problem, an Ant Colony Optimization (ACO) method is used to find the optimum path between the selected inspection windows. The method proposed in this paper is compared against relevant published work, and it is shown to yield better results.

Printed Circuit Board (PCB) testing has traditionally relied on manual inspection methods, which are often timeconsuming, error-prone, and costly. These limitations result in longer processing times, increased production costs, and inconsistent quality assurance. To address these challenges, this paper proposes a Generative AI-Based PCB Testing (GABPT) system designed to automate defect detection and classification in PCBs. The system leverages high-resolution image acquisition, advanced AI-powered image processing, and classification algorithms to identify common defects such as scratches, missing holes, broken paths, mouse bites, short circuits, and absent conductors. Utilizing a Quad ARM Cortex-A72 processor, the system processes captured PCB images in realtime and delivers immediate feedback on defects. The GABPT system aims to reduce human error, accelerate the inspection process, and minimize testing costs. It emphasizes efficient image preprocessing, precise image analysis, and hardware-software integration for reliable defect detection. By automating PCB inspection, the proposed system enhances testing accuracy, promotes cost-effective production, and supports sustainable manufacturing practices, ultimately contributing to the delivery of higher-quality electronic products.

Image registration technology has been widely used in many parts of the computer vision system such as the automatic optical inspection system which is used to detect the printed circuit board (PCB) defects. The accuracy of the image registration will deeply influence the system's performance, so this study proposed an accurate image registration algorithm and applied it to the PCB defect detection. Good features to track feature detector and speeded up robust feature descriptor are combined to extract efficient features to achieve the first accurate image registration. Afterwards, cross‐correlation functions were used to compute the shift between the reference image and the first‐registered image for further accurate registration. Experimental results show that the authors’ algorithm performs a much better registration, with a lower root‐mean‐square error value between the reference image and transformed image. What is more, they applied it to detect the defects of PCB with a high accuracy.

In recent years, the development of low cost consumer electronic products such as television, mobile, washing machine etc. make high demands on manufacturing of defect free Printed Circuit Board and Printed Circuit Board Assembly. Therefore, it is necessary to know the different types of defects and defect detection techniques of Printed Circuit Board in order to produce high quality zero defect printed circuit boards. This paper discusses various methods which have been used in detecting defects so as to understand the gaps which would be helpful for the researchers to do the future work related to defect detection.

A popular soldering technique for printed circuit boards (PCB) is the so-called surface-mounted technology. After the soldering process an automated optical inspection (AOI) is the common method determining whether a PCB shall go to a manual inspection and rework station (MIS) or can directly go further to the next process step. Thereby, the AOI is a vision-based system deriving user defined physical measurements from a camera image. Based on these pre-defined measurements associated with static specification limits, the AOI labels each inspected soldering spot on a PCB as non-defect or defect. However, a large majority of PCBs are wrongly labelled defect, so-called false calls, causing a major manual labour effort at the MIS.This dataset contains a 132-days recording of PCBs going through the MIS labelled as true defect or false call with the physical measurement by the AOI. Furthermore, the dataset may contain various distribution drifts of unknown type that can be explained by the high sensitivity of electronic production to small external factors that may change unrecognized and additionally the dataset has an unknown percentage of label error due the human labelling process.