Convolutional neural networks for electronic component classification

Abstract

This article presents an approach based on convolutional neural networks (CNN) for classifying electronic components. The objective is to develop an intelligent system capable of identifying electronic components in diverse environments. This task can benefit process efficiency in education and inventory control applications in the electronics industry. The dataset was created using both internet and proper images to improve the training and evaluation of the proposed model. The results were then compared to those of the pre-trained network MobileNetV2. The findings indicate that the artificial neural networks achieved high accuracy in detecting electronic components by using the transfer learning technique.