CNN-DFT Based Approach Applied to Image Inspection of Railcar Component: A Comparison with Machine Learning Methods

Authors

  • Rafael Rocha Federal University of Pará - UFPA
  • Cleison Silva Federal University of Pará - UFPA
  • Ana Gomes SENAI Innovation Institute for Mineral Technologies
  • Bruno Ferreira SENAI Innovation Institute for Mineral Technologies
  • Eduardo Carvalho SENAI Innovation Institute for Mineral Technologies
  • Ana Siravenha Vale Institute of Technology
  • Carolina Coelho da Rosa UFPA - CAMTUC - Faculdade de Engenharia Civil

Abstract

The railcar component inspection is one of the most critical tasks in railway maintenance. The use of processing, coupled with machine learning has emerged as a solution for replacing current standard methodologies. The spectral analysis gives the frequency representation of a signal and has been largely used in signal processing tasks. In this sense, this work proposes the evaluation of the use of the discrete Fourier transform (DFT) in addition to the spatial representation image of railcar component for an automatic detector of defective parts performed by convolutional neural network (CNN) classification. The most appropriate combination of images of the spatial and frequency domains is compared to the HOG feature descriptor linked to the multilayer perceptron (MLP) and support vector machine (SVM) classification, where data augmentation is investigated to improve the classification performed by all approaches. The results are given in measure of accuracy in addition to accuracy boxplot, and it showed encouraging results in the combination of spatial image and DFT magnitude combined with data augmentation as CNN inputs, reaching an accuracy of .

Downloads

Download data is not yet available.

Downloads

Published

2021-02-14