Influence of Image Pre-processing to Improve the Accuracy in a Convolutional Neural Network

  • Felipe Arias Del Campo Universidad Autónoma de Ciudad Juárez, Instituto de Ingeniería y Tecnología, Doctorado en Ciencias en Ingeniería (DOCIA) https://orcid.org/0000-0002-6787-8809
  • Osslan Osiris Vergara Universidad Autónoma de Ciudad Juárez, Instituto de Ingeniería y Tecnología, Departamento de Ingeniería Industrial y Manufactura
  • Vianey Guadalupe Cruz Universidad Autónoma de Ciudad Juárez, Instituto de Ingeniería y Tecnología, Departamento de Ingeniería Eléctrica y Computación
  • Lorenzo Antonio García Universidad Autónoma de Ciudad Juárez, Instituto de Ingeniería y Tecnología, Departamento de Ingeniería Industrial y Manufactura
  • Manuel Nandayapa Universidad Autónoma de Ciudad Juárez, Instituto de Ingeniería y Tecnología, Departamento de Ingeniería Industrial y Manufactura
Keywords: image pre-processing, quantization, sharpness enhancement, wavelet transform

Abstract

Convolutional neural networks (CNN) have been applied in different fields including image recognition. A CNN requires a set of images that will be used to teach to classify it into specific categories. However, the question about how image pre-processing influences CNN accuracy has not yet been answered bluntly. This paper proposes the application of pre-processing methods for the images’ feed to a CNN in order to improve the accuracy of the classification. Two methods of pre-processing are evaluated, quantization and sharpness enhancement. Quantization carries out at 7 levels, and sharpness works with four levels using the discrete wavelet transform. The tests were implemented with two CNN models, LeNet-5 and ResNet-50. In the first part of this paper the methodology and description of the CNN models, as well as the data set are presented. Later the descriptions of the experiments are presented. Finally, it is shown how the proposed method achieved an improvement on the accuracy compared with the results obtained with the images with no modification. The proposed pre-processing methods had an improvement between 1.35 and 3.1% on the validation accuracy.

Published
2019-10-16
How to Cite
Arias Del Campo, F., Vergara, O., Cruz, V., García, L., & Nandayapa, M. (2019). Influence of Image Pre-processing to Improve the Accuracy in a Convolutional Neural Network. International Journal of Combinatorial Optimization Problems and Informatics, 11(1), 88-96. Retrieved from https://ijcopi.org/index.php/ojs/article/view/162
Section
Articles