Automatic Optical Inspection for Defective PCB Detection Using Transfer Learning

Silva, Leandro H. de S.; Azevedo, George Oliveira de Araújo; Fernandes, Bruno; Bezerra, Byron Leite Dantas; Lima, Estanislau; Oliveira, Sérgio Campello

doi:10.1109/la-cci47412.2019.9037036

Cited by 22 publications

(10 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…15 to obtain an informed estimation for the decision threshold. We can confirm this by comparing the obtained ROC, AUC and detection accuracy to similar [38] or superior [22], [39] to that published in previous works, with the advantage of being completely non-intrusive. The mentioned works are also limited regarding the class of anomaly they can detect.…”

Section: Discussionsupporting

confidence: 81%

Non-intrusive Embedded Systems Anomaly Detection using Thermography and Machine Learning

Oliveira¹,

Bastos-Filho²,

Oliveira³

2021

Anais Do 15. Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

Quality control in electronic system manufacturing is achieved mainly through system testing. Device miniaturization and multilayer Printed Circuit Boards have increased the electronic circuit test complexity considerably and processes based on manual inspections have become outdated and inefficient. The concept of Industry 4.0 has enabled the manufacturing of customized products based on customers’ demands, which demands a high degree of flexibility in production processes, with low cost and without placing numerous test points. In this paper, we propose two automated test solutions based on machine learning and thermographic analysis. We propose deploying autoencoders and random forest in two different manners to detect firmware or hardware anomalies based on the circuit board’s temperature signature. We validate our proposal using two firmware versions running independently on the test board. We obtained an anomaly detection rate above 98%. In the random forest approach, we require all data classes for training, whereas the autoencoder only requires the reference class, which is expected in real scenarios.

show abstract

Section: Discussionsupporting

confidence: 81%

Non-intrusive Embedded Systems Anomaly Detection using Thermography and Machine Learning

Oliveira¹,

Bastos-Filho²,

Oliveira³

2021

Anais Do 15. Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

show abstract

“…Silva et al [27] apply principles of transfer learning and VGG16/ResNet-50 pre-trained models for identifying the defective PCBs and also non-referential method for inspection. Findings related the queries "printed circuit board and testing" and "PCB and testing" are summarized in Table 1 as the method/methodologies for testing and their aim are presented.…”

Section: Exploration Regarding Testing Of Pcbsmentioning

confidence: 99%

Printed circuit board and printed circuit board assembly methods for testing and visual inspection: a review

Petkov,

Ivanova

2024

Bulletin EEI

View full text Add to dashboard Cite

Testing and visual inspection of printed circuit boards (PCBs) and printed circuit board assemblies (PCBAs) are important procedures in the manufacturing process of electronic modules and devices related to locating and identifying possible defects and failures. Earlier defects detection leads to decreasing expenses, time and used resources to produce high quality electronics. In this paper an exploration and analysis about the current research regarding methods for PCB and PCBA testing, techniques for defects detection and vusial inspection is performed. The impact of machine and deep learning for testing and visual inspection procedures is also investigated. The used methodology comprises bibliometric approach and content analysis of papers, indexed in scientific database Scopus, considering the queries: “PCB and testing” and “PCB and testing”, “printed circuit board assembly and testing” and “PCBA and testing”, “PCB defect detection” and “PCBA defect detection”, “PCB and visual inspection”, and “PCBA and visual inspection”. The findings are presented in the form of a framework, which summarizes the contemporary landscape of methods for PCBs and PCBAs testing and visual inspection.

show abstract

“…One challenge using DL models is the huge amount of data required to optimize the model. Different approaches address this issue through transfer-learning [24,25], avoiding the need for huge datasets. Transfer-learning [26] allows the optimization of previously settled model parameters over a new data distribution domain.…”

Section: Deep Learningmentioning

confidence: 99%

Diabetic Retinopathy Improved Detection Using Deep Learning

et al. 2021

View full text Add to dashboard Cite

Diabetes is a disease that occurs when the body presents an uncontrolled level of glucose that is capable of damaging the retina, leading to permanent damage of the eyes or vision loss. When diabetes affects the eyes, it is known as diabetic retinopathy, which became a global medical problem among elderly people. The fundus oculi technique involves observing the eyeball to diagnose or check the pathology evolution. In this work, we implement a convolutional neural network model to process a fundus oculi image to recognize the eyeball structure and determine the presence of diabetic retinopathy. The model’s parameters are optimized using the transfer-learning methodology for mapping an image with the corresponding label. The model training and testing are performed with a dataset of medical fundus oculi images and a pathology severity scale present in the eyeball as labels. The severity scale separates the images into five classes, from a healthy eyeball to a proliferative diabetic retinopathy presence. The latter is probably a blind patient. Our proposal presented an accuracy of 97.78%, allowing for the confident prediction of diabetic retinopathy in fundus oculi images.

show abstract

Automatic Optical Inspection for Defective PCB Detection Using Transfer Learning

Cited by 22 publications

References 9 publications

Non-intrusive Embedded Systems Anomaly Detection using Thermography and Machine Learning

Non-intrusive Embedded Systems Anomaly Detection using Thermography and Machine Learning

Printed circuit board and printed circuit board assembly methods for testing and visual inspection: a review

Diabetic Retinopathy Improved Detection Using Deep Learning

Contact Info

Product

Resources

About