Electronic Components Detection Using Various Deep Learning Based Neural Network Models DOI Open Access
Fatih Uysal

International Journal of Computational and Experimental Science and Engineering, Год журнала: 2025, Номер 11(1)

Опубликована: Янв. 22, 2025

Electronic components of different sizes and types can be used in microelectronics, nanoelectronics, medical electronics, optoelectronics. For this reason, accurate detection all electronic such as transistors, capacitors, resistors, light-emitting diodes chips is great importance. purpose, study, an open source dataset was for the five components. In order to increase amount dataset, firstly, data augmentation processes were performed by rotating component images at certain angles right left directions. After these processes, multi-class classifications using deep learning based neural network models, namely Vision Transformer, MobileNetV2, EfficientNet, Swin Transformer Data-efficient Image Transformer. As a result with various necessary evaluation metrics precision, recall, f1-score accuracy obtained each model, highest value 0.992 model.

Язык: Английский

Electronic Components Detection Using Various Deep Learning Based Neural Network Models DOI Open Access
Fatih Uysal

International Journal of Computational and Experimental Science and Engineering, Год журнала: 2025, Номер 11(1)

Опубликована: Янв. 22, 2025

Electronic components of different sizes and types can be used in microelectronics, nanoelectronics, medical electronics, optoelectronics. For this reason, accurate detection all electronic such as transistors, capacitors, resistors, light-emitting diodes chips is great importance. purpose, study, an open source dataset was for the five components. In order to increase amount dataset, firstly, data augmentation processes were performed by rotating component images at certain angles right left directions. After these processes, multi-class classifications using deep learning based neural network models, namely Vision Transformer, MobileNetV2, EfficientNet, Swin Transformer Data-efficient Image Transformer. As a result with various necessary evaluation metrics precision, recall, f1-score accuracy obtained each model, highest value 0.992 model.

Язык: Английский

Процитировано

1