Advanced search
1 file | 674.49 KB

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

Author
Organization
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.
Keywords
Classification, Deep learning, Convolutional Neural Networks (CNNs), preprocessing, handwritten digits, data augmentation, RECOGNITION

Downloads

  • 25867315.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 674.49 KB

Citation

Please use this url to cite or link to this publication:

Chicago
Tabik, Siham, Daniel Peralta, Andrés Herrera-Poyatos, and Francisco Herrera. 2017. “A Snapshot of Image Pre-processing for Convolutional Neural Networks : Case Study of MNIST.” International Journal of Computational Intelligence Systems 10 (1): 555–568.
APA
Tabik, S., Peralta, D., Herrera-Poyatos, A., & Herrera, F. (2017). A snapshot of image pre-processing for convolutional neural networks : case study of MNIST. INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS, 10(1), 555–568.
Vancouver
1.
Tabik S, Peralta D, Herrera-Poyatos A, Herrera F. A snapshot of image pre-processing for convolutional neural networks : case study of MNIST. INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS. 2017;10(1):555–68.
MLA
Tabik, Siham, Daniel Peralta, Andrés Herrera-Poyatos, et al. “A Snapshot of Image Pre-processing for Convolutional Neural Networks : Case Study of MNIST.” INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS 10.1 (2017): 555–568. Print.
@article{8565711,
  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.},
  author       = {Tabik, Siham and Peralta, Daniel and Herrera-Poyatos, Andr{\'e}s and Herrera, Francisco},
  issn         = {1875-6891},
  journal      = {INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS},
  language     = {eng},
  number       = {1},
  pages        = {555--568},
  title        = {A snapshot of image pre-processing for convolutional neural networks : case study of MNIST},
  url          = {http://dx.doi.org/10.2991/ijcis.2017.10.1.38},
  volume       = {10},
  year         = {2017},
}

Altmetric
View in Altmetric
Web of Science
Times cited: