Show simple item record

dc.contributor.authorTabik, Siham 
dc.contributor.authorPeralta, Daniel
dc.contributor.authorHerrera-Poyatos, Andrés
dc.contributor.authorHerrera Triguero, Francisco
dc.identifier.citationTabik, 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. []es_ES
dc.description.abstractIn 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.es_ES
dc.description.sponsorshipSpanish Government TIN2014-524 57251-Pes_ES
dc.description.sponsorshipAndalusian Research Plans P11-TIC-7765es_ES
dc.description.sponsorshipSpanish Government RYC-2015-18136es_ES
dc.publisherAtlantis Presses_ES
dc.rightsAtribución-NoComercial 3.0 España*
dc.subjectClassification es_ES
dc.subjectDeep learninges_ES
dc.subjectConvolutional Neural Networks (CNNs)es_ES
dc.subjectHandwritten digitses_ES
dc.subjectData augmentationes_ES
dc.titleA snapshot of image pre-processing for convolutional neural networks: case study of MNISTes_ES

Files in this item


This item appears in the following Collection(s)

Show simple item record

Atribución-NoComercial 3.0 España
Except where otherwise noted, this item's license is described as Atribución-NoComercial 3.0 España