Segmentation Methods for Image Classification Using a Convolutional Neural Network on AR-Sandbox - Artificial Intelligence Applications and Innovations Access content directly
Conference Papers Year : 2019

Segmentation Methods for Image Classification Using a Convolutional Neural Network on AR-Sandbox

Abstract

Fields such as early education and motor rehabilitation provide a space for their integration with augmented reality devices as AR-Sandbox, in order to provide support to these fields, generating a feedback of tasks carried out through the recognition of images based on convolutional neural networks. However, the nature of the AR-Sandbox generates a high noise level of the acquired images, for this reason the present study has as purpose the implementation and comparison of three segmentation methods (Canny Edge Detector, Color-space and Threshold) for the training and prediction phase of a convolutional neural network model previously established. When carrying out this study, it was obtained that the combined model with color-space segmentation presents an average percentage of 99% performance for the classification of vowels, described by the AUC of the ROC curve, this being the model with the best performance.
Fichier principal
Vignette du fichier
483292_1_En_33_Chapter.pdf (605.79 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02331321 , version 1 (24-10-2019)

Licence

Attribution

Identifiers

Cite

Andres Ovidio Restrepo Rodriguez, Daniel Esteban Casas Mateus, Paulo Alonso Gaona-García, Adriana Gomez Acosta, Carlos Enrique Montenegro Marin. Segmentation Methods for Image Classification Using a Convolutional Neural Network on AR-Sandbox. 15th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), May 2019, Hersonissos, Greece. pp.391-398, ⟨10.1007/978-3-030-19823-7_33⟩. ⟨hal-02331321⟩
52 View
34 Download

Altmetric

Share

Gmail Facebook X LinkedIn More