Automatic image filtering on social networks using deep learning and perceptual hashing during crises

Dat T. Nguyen, Firoj Alam, Ferda Ofli, Muhammad Imran

Research output: Contribution to journalConference article

7 Citations (Scopus)

Abstract

The extensive use of social media platforms, especially during disasters, creates unique opportunities for humanitarian organizations to gain situational awareness and launch relief operations accordingly. In addition to the textual content, people post overwhelming amounts of imagery data on social networks within minutes of a disaster hit. Studies point to the importance of this online imagery content for emergency response. Despite recent advances in the computer vision field, automatic processing of the crisis-related social media imagery data remains a challenging task. It is because a majority of which consists of redundant and irrelevant content. In this paper, we present an image processing pipeline that comprises de-duplication and relevancy filtering mechanisms to collect and filter social media image content in real-time during a crisis event. Results obtained from extensive experiments on real-world crisis datasets demonstrate the significance of the proposed pipeline for optimal utilization of both human and machine computing resources.

Original languageEnglish
Pages (from-to)499-511
Number of pages13
JournalProceedings of the International ISCRAM Conference
Volume2017-May
Publication statusPublished - 1 Jan 2017

Fingerprint

Disasters
Pipelines
Computer vision
Image processing
Processing
Experiments
Deep learning
Social networks
Social media
Imagery
Disaster

Keywords

  • Disaster management
  • Image processing
  • Social media
  • Supervised classification

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Information Systems and Management
  • Electrical and Electronic Engineering

Cite this

Automatic image filtering on social networks using deep learning and perceptual hashing during crises. / Nguyen, Dat T.; Alam, Firoj; Ofli, Ferda; Imran, Muhammad.

In: Proceedings of the International ISCRAM Conference, Vol. 2017-May, 01.01.2017, p. 499-511.

Research output: Contribution to journalConference article

@article{9e45013745a649a2893191b7081ee053,
title = "Automatic image filtering on social networks using deep learning and perceptual hashing during crises",
abstract = "The extensive use of social media platforms, especially during disasters, creates unique opportunities for humanitarian organizations to gain situational awareness and launch relief operations accordingly. In addition to the textual content, people post overwhelming amounts of imagery data on social networks within minutes of a disaster hit. Studies point to the importance of this online imagery content for emergency response. Despite recent advances in the computer vision field, automatic processing of the crisis-related social media imagery data remains a challenging task. It is because a majority of which consists of redundant and irrelevant content. In this paper, we present an image processing pipeline that comprises de-duplication and relevancy filtering mechanisms to collect and filter social media image content in real-time during a crisis event. Results obtained from extensive experiments on real-world crisis datasets demonstrate the significance of the proposed pipeline for optimal utilization of both human and machine computing resources.",
keywords = "Disaster management, Image processing, Social media, Supervised classification",
author = "Nguyen, {Dat T.} and Firoj Alam and Ferda Ofli and Muhammad Imran",
year = "2017",
month = "1",
day = "1",
language = "English",
volume = "2017-May",
pages = "499--511",
journal = "Proceedings of the International ISCRAM Conference",
issn = "2411-3387",

}

TY - JOUR

T1 - Automatic image filtering on social networks using deep learning and perceptual hashing during crises

AU - Nguyen, Dat T.

AU - Alam, Firoj

AU - Ofli, Ferda

AU - Imran, Muhammad

PY - 2017/1/1

Y1 - 2017/1/1

N2 - The extensive use of social media platforms, especially during disasters, creates unique opportunities for humanitarian organizations to gain situational awareness and launch relief operations accordingly. In addition to the textual content, people post overwhelming amounts of imagery data on social networks within minutes of a disaster hit. Studies point to the importance of this online imagery content for emergency response. Despite recent advances in the computer vision field, automatic processing of the crisis-related social media imagery data remains a challenging task. It is because a majority of which consists of redundant and irrelevant content. In this paper, we present an image processing pipeline that comprises de-duplication and relevancy filtering mechanisms to collect and filter social media image content in real-time during a crisis event. Results obtained from extensive experiments on real-world crisis datasets demonstrate the significance of the proposed pipeline for optimal utilization of both human and machine computing resources.

AB - The extensive use of social media platforms, especially during disasters, creates unique opportunities for humanitarian organizations to gain situational awareness and launch relief operations accordingly. In addition to the textual content, people post overwhelming amounts of imagery data on social networks within minutes of a disaster hit. Studies point to the importance of this online imagery content for emergency response. Despite recent advances in the computer vision field, automatic processing of the crisis-related social media imagery data remains a challenging task. It is because a majority of which consists of redundant and irrelevant content. In this paper, we present an image processing pipeline that comprises de-duplication and relevancy filtering mechanisms to collect and filter social media image content in real-time during a crisis event. Results obtained from extensive experiments on real-world crisis datasets demonstrate the significance of the proposed pipeline for optimal utilization of both human and machine computing resources.

KW - Disaster management

KW - Image processing

KW - Social media

KW - Supervised classification

UR - http://www.scopus.com/inward/record.url?scp=85030697324&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85030697324&partnerID=8YFLogxK

M3 - Conference article

VL - 2017-May

SP - 499

EP - 511

JO - Proceedings of the International ISCRAM Conference

JF - Proceedings of the International ISCRAM Conference

SN - 2411-3387

ER -