Title: Hand-drawn electronic component recognition using deep learning algorithm

Authors: Haiyan Wang; Tianhong Pan; Mian Khuram Ahsan

Addresses: School of Electrical Engineering and Automation, Anhui University, Hefei, Anhui 230601, China; School of Electrical and Information Engineering, Jiangsu University, Zhenjiang, Jiangsu 212013, China ' School of Electrical Engineering and Automation, Anhui University, Hefei, Anhui 230601, China; School of Electrical and Information Engineering, Jiangsu University, Zhenjiang, Jiangsu 212013, China ' School of Electrical and Information Engineering, Jiangsu University, Zhenjiang, Jiangsu 212013, China

Abstract: Hand-drawn circuit recognition plays an increasingly important role in circuit design work and electrical knowledge teaching. Hand-drawn electronic component recognition is an indispensable part of hand-drawn circuit recognition. Accurate electronic component recognition ensures accurate circuit recognition. In this paper, a hand-drawn electronic component recognition method using a Convolutional Neural Network (CNN) and a softmax classifier is proposed. The CNN composed of a convolutional layer, an activation layer and an average-pooling layer is designed to extract features of a hand-drawn electronic component image. The kernel function for the CNN is obtained by a sparse auto-encoder method. A softmax classifier is trained for classification based on the features extracted by the CNN. The recognition method can identify rotating electronic components because of the added rotated image and achieve 95% recognition accuracy.

Keywords: electronic component recognition; CNN; convolutional neural network; aparse auto-encoder.

DOI: 10.1504/IJCAT.2020.103905

International Journal of Computer Applications in Technology, 2020 Vol.62 No.1, pp.13 - 19

Received: 21 Sep 2018
Accepted: 08 Mar 2019

Published online: 28 Nov 2019 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article