A snapshot of image pre-processing for convolutional neural networks: case study of MNIST
MetadatosAfficher la notice complète
ClassificationDeep learningConvolutional Neural Networks (CNNs)PreprocessingHandwritten digitsData augmentation
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. [https://doi.org/10.2991/ijcis.2017.10.1.38]
PatrocinadorSpanish Government TIN2014-524 57251-P; Andalusian Research Plans P11-TIC-7765; Spanish Government RYC-2015-18136
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.