Investigating human factors in image forgery detection

Parag Shridhar Chandakkar, Baoxin Li

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

1 Citation (Scopus)

Abstract

In today's age of internet and social media, one can find an enormous volume of forged images on-line. These images have been used in the past to convey falsified information and achieve harmful intentions. The spread and the effect of the social media only makes this problem more severe. While creating forged images has become easier due to software advancements, there is no automated algorithm which can reliably detect forgery. Image forgery detection can be seen as a subset of image understanding problem. Human performance is still the gold-standard for these type of problems when compared to existing state-of-art automated algorithms. We conduct a subjective evaluation test with the aid of eye-tracker to in- vestigate into human factors associated with this problem. We compare the performance of an automated algorithm and humans for forgery detection problem. We also develop an algorithm which uses the data from the evaluation test to predict the difficulty-level of an image1. The experimental results presented in this paper should facilitate development of better algorithms in the future.

Original languageEnglish (US)
Title of host publicationHuEvent 2014 - Proceedings of the 2014 Workshop on Human Centered Event Understanding from Multimedia
PublisherAssociation for Computing Machinery, Inc
Pages41-44
Number of pages4
ISBN (Print)9781450331203
DOIs
StatePublished - Nov 7 2014
Event1st ACM International Workshop on Human Centered Event Understanding from Multimedia, HuEvent 2014 - Orlando, United States
Duration: Nov 7 2014 → …

Other

Other1st ACM International Workshop on Human Centered Event Understanding from Multimedia, HuEvent 2014
CountryUnited States
CityOrlando
Period11/7/14 → …

Fingerprint

Human engineering
Image understanding
Gold
Internet

Keywords

  • Eye-tracking
  • Image forgery
  • Subjective evaluation

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction

Cite this

Chandakkar, P. S., & Li, B. (2014). Investigating human factors in image forgery detection. In HuEvent 2014 - Proceedings of the 2014 Workshop on Human Centered Event Understanding from Multimedia (pp. 41-44). Association for Computing Machinery, Inc. https://doi.org/10.1145/2660505.2660510

Investigating human factors in image forgery detection. / Chandakkar, Parag Shridhar; Li, Baoxin.

HuEvent 2014 - Proceedings of the 2014 Workshop on Human Centered Event Understanding from Multimedia. Association for Computing Machinery, Inc, 2014. p. 41-44.

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

Chandakkar, PS & Li, B 2014, Investigating human factors in image forgery detection. in HuEvent 2014 - Proceedings of the 2014 Workshop on Human Centered Event Understanding from Multimedia. Association for Computing Machinery, Inc, pp. 41-44, 1st ACM International Workshop on Human Centered Event Understanding from Multimedia, HuEvent 2014, Orlando, United States, 11/7/14. https://doi.org/10.1145/2660505.2660510
Chandakkar PS, Li B. Investigating human factors in image forgery detection. In HuEvent 2014 - Proceedings of the 2014 Workshop on Human Centered Event Understanding from Multimedia. Association for Computing Machinery, Inc. 2014. p. 41-44 https://doi.org/10.1145/2660505.2660510
Chandakkar, Parag Shridhar ; Li, Baoxin. / Investigating human factors in image forgery detection. HuEvent 2014 - Proceedings of the 2014 Workshop on Human Centered Event Understanding from Multimedia. Association for Computing Machinery, Inc, 2014. pp. 41-44
@inproceedings{6b11d69b874740ccaa066590ea3c114c,
title = "Investigating human factors in image forgery detection",
abstract = "In today's age of internet and social media, one can find an enormous volume of forged images on-line. These images have been used in the past to convey falsified information and achieve harmful intentions. The spread and the effect of the social media only makes this problem more severe. While creating forged images has become easier due to software advancements, there is no automated algorithm which can reliably detect forgery. Image forgery detection can be seen as a subset of image understanding problem. Human performance is still the gold-standard for these type of problems when compared to existing state-of-art automated algorithms. We conduct a subjective evaluation test with the aid of eye-tracker to in- vestigate into human factors associated with this problem. We compare the performance of an automated algorithm and humans for forgery detection problem. We also develop an algorithm which uses the data from the evaluation test to predict the difficulty-level of an image1. The experimental results presented in this paper should facilitate development of better algorithms in the future.",
keywords = "Eye-tracking, Image forgery, Subjective evaluation",
author = "Chandakkar, {Parag Shridhar} and Baoxin Li",
year = "2014",
month = "11",
day = "7",
doi = "10.1145/2660505.2660510",
language = "English (US)",
isbn = "9781450331203",
pages = "41--44",
booktitle = "HuEvent 2014 - Proceedings of the 2014 Workshop on Human Centered Event Understanding from Multimedia",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - Investigating human factors in image forgery detection

AU - Chandakkar, Parag Shridhar

AU - Li, Baoxin

PY - 2014/11/7

Y1 - 2014/11/7

N2 - In today's age of internet and social media, one can find an enormous volume of forged images on-line. These images have been used in the past to convey falsified information and achieve harmful intentions. The spread and the effect of the social media only makes this problem more severe. While creating forged images has become easier due to software advancements, there is no automated algorithm which can reliably detect forgery. Image forgery detection can be seen as a subset of image understanding problem. Human performance is still the gold-standard for these type of problems when compared to existing state-of-art automated algorithms. We conduct a subjective evaluation test with the aid of eye-tracker to in- vestigate into human factors associated with this problem. We compare the performance of an automated algorithm and humans for forgery detection problem. We also develop an algorithm which uses the data from the evaluation test to predict the difficulty-level of an image1. The experimental results presented in this paper should facilitate development of better algorithms in the future.

AB - In today's age of internet and social media, one can find an enormous volume of forged images on-line. These images have been used in the past to convey falsified information and achieve harmful intentions. The spread and the effect of the social media only makes this problem more severe. While creating forged images has become easier due to software advancements, there is no automated algorithm which can reliably detect forgery. Image forgery detection can be seen as a subset of image understanding problem. Human performance is still the gold-standard for these type of problems when compared to existing state-of-art automated algorithms. We conduct a subjective evaluation test with the aid of eye-tracker to in- vestigate into human factors associated with this problem. We compare the performance of an automated algorithm and humans for forgery detection problem. We also develop an algorithm which uses the data from the evaluation test to predict the difficulty-level of an image1. The experimental results presented in this paper should facilitate development of better algorithms in the future.

KW - Eye-tracking

KW - Image forgery

KW - Subjective evaluation

UR - http://www.scopus.com/inward/record.url?scp=84945396573&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84945396573&partnerID=8YFLogxK

U2 - 10.1145/2660505.2660510

DO - 10.1145/2660505.2660510

M3 - Conference contribution

AN - SCOPUS:84945396573

SN - 9781450331203

SP - 41

EP - 44

BT - HuEvent 2014 - Proceedings of the 2014 Workshop on Human Centered Event Understanding from Multimedia

PB - Association for Computing Machinery, Inc

ER -