Desenvolvimento de uma API utilizando uma Rede Neural Convolucional YOLOv7 para Detecção de Defeitos em Placas de Circuito Impresso
This work presents a method for defect detection in printed circuit boards (PCBs) using the YOLOv7 convolutional neural network and an API developed with FastAPI. The methodology involves data collection and annotation, training the YOLOv7 model, and implementing an efficient API for inference. The...
| Autor principal: | Guimarães, Fabrício da Costa |
|---|---|
| Grau: | Trabalho de Conclusão de Curso |
| Idioma: | por |
| Publicado em: |
Brasil
2024
|
| Assuntos: | |
| Acesso em linha: |
http://riu.ufam.edu.br/handle/prefix/7638 |
| Resumo: |
|---|
|
This work presents a method for defect detection in printed circuit boards (PCBs) using the YOLOv7 convolutional neural network and an API developed with FastAPI. The methodology involves data collection and annotation, training the YOLOv7 model, and implementing an efficient API for inference. The results demonstrate high precision, recall and f1-score in defect detection, with mAP@0.5 of 0.9431 and mAP@0.5:0.95 of 0.4814. The main contributions of this work are the efficient implementation of a defect detection model for PCBs and the creation of an API for industrial and scientific applications. |