A snapshot of image pre-processing for convolutional neural networks: case study of MNIST

DOI

10.2991/ijcis.2017.10.1.38How to use a DOI?

Keywords

Classification; Deep learning; Convolutional Neural Networks (CNNs); preprocessing; handwritten digits; data augmentation

Abstract

In the last five years, deep learning methods and particularly Convolutional Neural Networks (CNNs) have exhibited excellent accuracies in many pattern classification problems. Most of the state-of-the-art models apply data-augmentation techniques at the training stage. This paper provides a brief tutorial on data preprocessing and shows its benefits by using the competitive MNIST handwritten digits classification problem. We show and analyze the impact of different preprocessing techniques on the performance of three CNNs, LeNet, Network3 and DropConnect, together with their ensembles. The analyzed transformations are, centering, elastic deformation, translation, rotation and different combinations of them. Our analysis demonstrates that data-preprocessing techniques, such as the combination of elastic deformation and rotation, together with ensembles have a high potential to further improve the state-of-the-art accuracy in MNIST classification.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article under the CC BY-NC license (http://creativecommons.org/licences/by-nc/4.0/).

Download article (PDF)
View full text (HTML)

TY  - JOUR
AU  - Siham Tabik
AU  - Daniel Peralta
AU  - Andrés Herrera-Poyatos
AU  - Francisco Herrera
PY  - 2017
DA  - 2017/01/01
TI  - A snapshot of image pre-processing for convolutional neural networks: case study of MNIST
JO  - International Journal of Computational Intelligence Systems
SP  - 555
EP  - 568
VL  - 10
IS  - 1
SN  - 1875-6883
UR  - https://doi.org/10.2991/ijcis.2017.10.1.38
DO  - 10.2991/ijcis.2017.10.1.38
ID  - Tabik2017
ER  -