Evaluation of Transfer Learning Scenarios in Plankton Image Classification

Francisco Caio Maia Rodrigues, Nina S. T. Hirata, Antonio A. Abello, Leandro T. De La Cruz, Rubens M. Lopes, R. Hirata Jr.

2018

Abstract

Automated in situ plankton image classification is a challenging task. To take advantage of recent progress in machine learning techniques, a large amount of labeled data is necessary. However, beyond being time consuming, labeling is a task that may require frequent redoing due to variations in plankton population as well as image characteristics. Transfer learning, which is a machine learning technique concerned with transferring knowledge obtained in some data domain to a second distinct data domain, appears as a potential approach to be employed in this scenario. We use convolutional neural networks, trained on publicly available distinct datasets, to extract features from our plankton image data and then train SVM classifiers to perform the classification. Results show evidences that indicate the effectiveness of transfer learning in real plankton image classification situations

Download


Paper Citation


in Harvard Style

Rodrigues F., Hirata N., Abello A., De La Cruz L., Lopes R. and Hirata Jr. R. (2018). Evaluation of Transfer Learning Scenarios in Plankton Image Classification. In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP; ISBN 978-989-758-290-5, SciTePress, pages 359-366. DOI: 10.5220/0006626703590366


in Bibtex Style

@conference{visapp18,
author={Francisco Caio Maia Rodrigues and Nina S. T. Hirata and Antonio A. Abello and Leandro T. De La Cruz and Rubens M. Lopes and R. Hirata Jr.},
title={Evaluation of Transfer Learning Scenarios in Plankton Image Classification},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP},
year={2018},
pages={359-366},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006626703590366},
isbn={978-989-758-290-5},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP
TI - Evaluation of Transfer Learning Scenarios in Plankton Image Classification
SN - 978-989-758-290-5
AU - Rodrigues F.
AU - Hirata N.
AU - Abello A.
AU - De La Cruz L.
AU - Lopes R.
AU - Hirata Jr. R.
PY - 2018
SP - 359
EP - 366
DO - 10.5220/0006626703590366
PB - SciTePress