Detecting Anomalous Regions from an Image based on Deep Captioning

Yusuke Hatae, Qingpu Yang, Muhammad Fikko Fadjrimiratno, Yuanyuan Li, Tetsu Matsukawa, Einoshin Suzuki

2020

Abstract

In this paper we propose a one-class anomalous region detection method from an image based on deep captioning. Such a method can be installed on an autonomous mobile robot, which reports anomalies from observation without any human supervision and would interest a wide range of researchers, practitioners, and users. In addition to image features, which were used by conventional methods, our method exploits recent advances in deep captioning, which is based on deep neural networks trained on a large-scale data on image - caption pairs, enabling anomaly detection in the semantic level. Incremental clustering is adopted so that the robot is able to model its observation into a set of clusters and report substantially new observations as anomalies. Extensive experiments using two real-world data demonstrate the superiority of our method in terms of recall, precision, F measure, and AUC over the traditional approach. The experiments also show that our method exhibits excellent learning curve and low threshold dependency.

Paper Citation

in Harvard Style

Hatae Y., Yang Q., Fadjrimiratno M., Li Y., Matsukawa T. and Suzuki E. (2020). Detecting Anomalous Regions from an Image based on Deep Captioning. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP; ISBN 978-989-758-402-2, SciTePress, pages 326-335. DOI: 10.5220/0008949603260335

in Bibtex Style

@conference{visapp20,
author={Yusuke Hatae and Qingpu Yang and Muhammad Fikko Fadjrimiratno and Yuanyuan Li and Tetsu Matsukawa and Einoshin Suzuki},
title={Detecting Anomalous Regions from an Image based on Deep Captioning},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP},
year={2020},
pages={326-335},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008949603260335},
isbn={978-989-758-402-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP
TI - Detecting Anomalous Regions from an Image based on Deep Captioning
SN - 978-989-758-402-2
AU - Hatae Y.
AU - Yang Q.
AU - Fadjrimiratno M.
AU - Li Y.
AU - Matsukawa T.
AU - Suzuki E.
PY - 2020
SP - 326
EP - 335
DO - 10.5220/0008949603260335
PB - SciTePress