Threat detection in episodic images

Gaukhar Madikenova, Aisulu Galimuratova, Martin Lukac

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Despite recent advances in computer vision humans still perform recognition of a novel scene in a single glance better than the best of the available systems. Consequently in order to achieve a similar ability in artificial intelligent systems, it is necessary to further study the low-level mechanisms in image processing for solving computer vision problems. The purpose of this study is to find an effective approach to classify images into threatening and non-threatening categories. Some of the existing algorithms for scene classification are examined and are studied in order to identify which is the best for the threatening context. We define a threat as a cause of harm or danger from a person or some phenomenon. We have constructed an image database containing hundreds of images labeled and divided into threatening and non-threatening categories. The results of classification shows that using some of the current state of art features and scene descriptors, the accuracy of classification is up to 80%.

Original languageEnglish
Title of host publicationIDT 2016 - Proceedings of the International Conference on Information and Digital Technologies 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages180-185
Number of pages6
ISBN (Electronic)9781467388603
DOIs
Publication statusPublished - Aug 31 2016
Event2016 International Conference on Information and Digital Technologies, IDT 2016 - Rzeszow, Poland
Duration: Jul 5 2016Jul 7 2016

Other

Other2016 International Conference on Information and Digital Technologies, IDT 2016
CountryPoland
CityRzeszow
Period7/5/167/7/16

Fingerprint

Computer vision
Intelligent systems
Image processing

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Signal Processing

Cite this

Madikenova, G., Galimuratova, A., & Lukac, M. (2016). Threat detection in episodic images. In IDT 2016 - Proceedings of the International Conference on Information and Digital Technologies 2016 (pp. 180-185). [7557170] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DT.2016.7557170

Threat detection in episodic images. / Madikenova, Gaukhar; Galimuratova, Aisulu; Lukac, Martin.

IDT 2016 - Proceedings of the International Conference on Information and Digital Technologies 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 180-185 7557170.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Madikenova, G, Galimuratova, A & Lukac, M 2016, Threat detection in episodic images. in IDT 2016 - Proceedings of the International Conference on Information and Digital Technologies 2016., 7557170, Institute of Electrical and Electronics Engineers Inc., pp. 180-185, 2016 International Conference on Information and Digital Technologies, IDT 2016, Rzeszow, Poland, 7/5/16. https://doi.org/10.1109/DT.2016.7557170
Madikenova G, Galimuratova A, Lukac M. Threat detection in episodic images. In IDT 2016 - Proceedings of the International Conference on Information and Digital Technologies 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 180-185. 7557170 https://doi.org/10.1109/DT.2016.7557170
Madikenova, Gaukhar ; Galimuratova, Aisulu ; Lukac, Martin. / Threat detection in episodic images. IDT 2016 - Proceedings of the International Conference on Information and Digital Technologies 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 180-185
@inproceedings{a93cc63193e5453789662f65c637e791,
title = "Threat detection in episodic images",
abstract = "Despite recent advances in computer vision humans still perform recognition of a novel scene in a single glance better than the best of the available systems. Consequently in order to achieve a similar ability in artificial intelligent systems, it is necessary to further study the low-level mechanisms in image processing for solving computer vision problems. The purpose of this study is to find an effective approach to classify images into threatening and non-threatening categories. Some of the existing algorithms for scene classification are examined and are studied in order to identify which is the best for the threatening context. We define a threat as a cause of harm or danger from a person or some phenomenon. We have constructed an image database containing hundreds of images labeled and divided into threatening and non-threatening categories. The results of classification shows that using some of the current state of art features and scene descriptors, the accuracy of classification is up to 80{\%}.",
author = "Gaukhar Madikenova and Aisulu Galimuratova and Martin Lukac",
year = "2016",
month = "8",
day = "31",
doi = "10.1109/DT.2016.7557170",
language = "English",
pages = "180--185",
booktitle = "IDT 2016 - Proceedings of the International Conference on Information and Digital Technologies 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Threat detection in episodic images

AU - Madikenova, Gaukhar

AU - Galimuratova, Aisulu

AU - Lukac, Martin

PY - 2016/8/31

Y1 - 2016/8/31

N2 - Despite recent advances in computer vision humans still perform recognition of a novel scene in a single glance better than the best of the available systems. Consequently in order to achieve a similar ability in artificial intelligent systems, it is necessary to further study the low-level mechanisms in image processing for solving computer vision problems. The purpose of this study is to find an effective approach to classify images into threatening and non-threatening categories. Some of the existing algorithms for scene classification are examined and are studied in order to identify which is the best for the threatening context. We define a threat as a cause of harm or danger from a person or some phenomenon. We have constructed an image database containing hundreds of images labeled and divided into threatening and non-threatening categories. The results of classification shows that using some of the current state of art features and scene descriptors, the accuracy of classification is up to 80%.

AB - Despite recent advances in computer vision humans still perform recognition of a novel scene in a single glance better than the best of the available systems. Consequently in order to achieve a similar ability in artificial intelligent systems, it is necessary to further study the low-level mechanisms in image processing for solving computer vision problems. The purpose of this study is to find an effective approach to classify images into threatening and non-threatening categories. Some of the existing algorithms for scene classification are examined and are studied in order to identify which is the best for the threatening context. We define a threat as a cause of harm or danger from a person or some phenomenon. We have constructed an image database containing hundreds of images labeled and divided into threatening and non-threatening categories. The results of classification shows that using some of the current state of art features and scene descriptors, the accuracy of classification is up to 80%.

UR - http://www.scopus.com/inward/record.url?scp=84988890219&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84988890219&partnerID=8YFLogxK

U2 - 10.1109/DT.2016.7557170

DO - 10.1109/DT.2016.7557170

M3 - Conference contribution

SP - 180

EP - 185

BT - IDT 2016 - Proceedings of the International Conference on Information and Digital Technologies 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -