Publication detail

SIFT and SURF based feature extraction for the anomaly detection

BILÍK, Š. HORÁK, K.

Original Title

SIFT and SURF based feature extraction for the anomaly detection

Type

conference paper

Language

English

Original Abstract

In this paper, we suggest a way to use SIFT and SURF algorithms to extract the image features for anomaly detection. We use those feature vectors to train various classifiers on a real-world dataset in the semi-supervised (with a small number of faulty samples) manner with a large number of classifiers and in the one-class (with no faulty samples) manner using the SVDD and SVM classifier. We prove, that the SIFT and SURF algorithms could be used as feature extractors, that they could be used to train a semi-supervised and one-class classifier with an accuracy around 89\% and that the performance of the one-class classifier could be comparable to the semi-supervised one. We also made our dataset and source code publicly available.

Keywords

Anomaly detection;Object descriptors;Machine Learning;SIFT;SURF

Authors

BILÍK, Š.; HORÁK, K.

Released

26. 4. 2022

Publisher

Brno University of Technology, Faculty of Electrical Engineering and Communication

Location

Brno

ISBN

978-80-214-6029-4

Book

Proceedings I of the 28 th Conference STUDENT EEICT 2022 General Papers

Edition

1

Pages from

459

Pages to

464

Pages count

6

URL

https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2022_sbornik_1.pdf

BibTex

@inproceedings{BUT177722,
  author="Šimon {Bilík} and Karel {Horák}",
  title="SIFT and SURF based feature extraction for the anomaly detection",
  booktitle="Proceedings I of the 28 th Conference STUDENT EEICT 2022 General Papers",
  year="2022",
  series="1",
  pages="459--464",
  publisher="Brno University of Technology, Faculty of Electrical Engineering and Communication",
  address="Brno",
  isbn="978-80-214-6029-4",
  url="https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2022_sbornik_1.pdf"
}