ELSA: Expanded Latent Space Autoencoder for Image Feature Extraction and Classification

Emerson Vilar de Oliveira, Dunfrey Aragão, Luiz Gonçalves

2024

Abstract

In the field of computer vision, image classification has been aiding in the understanding and labeling of images. Machine learning and artificial intelligence algorithms, especially artificial neural networks, are widely used tools for this task. In this work, we present the Expanded Latent space Autoencoder (ELSA). The ELSA network consists of more than one autoencoder in its internal structure, concatenating their latent spaces and constructing an expanded latent space. The expanded latent space aims to extract more information from input data. Thus, this expanded latent space can be used by other networks for general tasks such as prediction and classification. To evaluate these capabilities, we created an image classification network for the FashionM-NIST and MNIST datasets, achieving 99.97 and 99.98 accuracy for the test dataset. The classifier trained with the expanded latent space dataset outperforms some models in public benchmarks.

Paper Citation

in Harvard Style

Vilar de Oliveira E., Aragão D. and Gonçalves L. (2024). ELSA: Expanded Latent Space Autoencoder for Image Feature Extraction and Classification. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 703-710. DOI: 10.5220/0012455300003660

in Bibtex Style

@conference{visapp24,
author={Emerson Vilar de Oliveira and Dunfrey Aragão and Luiz Gonçalves},
title={ELSA: Expanded Latent Space Autoencoder for Image Feature Extraction and Classification},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2024},
pages={703-710},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012455300003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - ELSA: Expanded Latent Space Autoencoder for Image Feature Extraction and Classification
SN - 978-989-758-679-8
AU - Vilar de Oliveira E.
AU - Aragão D.
AU - Gonçalves L.
PY - 2024
SP - 703
EP - 710
DO - 10.5220/0012455300003660
PB - SciTePress