On the benchmarking of ResNet forgery image model using different datasets

Faria Hossain; Tasos Dagiuklas

doi:10.1109/HCCS55241.2022.10090275

On the benchmarking of ResNet forgery image model using different datasets

Faria Hossain, Tasos Dagiuklas

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

9 Downloads (Pure)

Abstract

This paper presents the benchmarking and improve- ment of the ResNet image forgery model using three different datasets (CASIA, Columbia, and LSBU). The model is based on classification, where forgery images have been edited using cut-paste modification technique.The images are categorized to check if the algorithm can successfully identify the difference between the original and the forgery image. All images have been pre-processed with Gray-Edge detectors to obtain get better classification results. Experimental results have shown that the Gray-edge technique has improved the accuracy across all image datasets.

Original language	English
Title of host publication	Proceedings - 2022 International Conference on Human-Centered Cognitive Systems, HCCS 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665450416
DOIs	https://doi.org/10.1109/HCCS55241.2022.10090275 https://doi.org/10.1109/HCCS55241.2022.10090275
Publication status	Published - 18 Dec 2022
Event	2022 International Conference on Human-Centered Cognitive Systems, HCCS 2022 - Shanghai, China Duration: 17 Dec 2022 → 18 Dec 2022

Publication series

Name	Proceedings - 2022 International Conference on Human-Centered Cognitive Systems, HCCS 2022

Conference

Conference	2022 International Conference on Human-Centered Cognitive Systems, HCCS 2022
Country/Territory	China
City	Shanghai
Period	17/12/22 → 18/12/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

Image Forgery
LSBU-Columbia-CASIA image datasets
ResNet

Access to Document

On the benchmarking of ResNet forgery image model using three different datasets (1)[13]Accepted author manuscript, 920 KBLicence: CC BY 4.0
On the benchmarking of ResNet forgery image model using three different datasets (1)[13]

Cite this

Hossain, F., & Dagiuklas, T. (2022). On the benchmarking of ResNet forgery image model using different datasets. In Proceedings - 2022 International Conference on Human-Centered Cognitive Systems, HCCS 2022 (Proceedings - 2022 International Conference on Human-Centered Cognitive Systems, HCCS 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/HCCS55241.2022.10090275, https://doi.org/10.1109/HCCS55241.2022.10090275

@inproceedings{6d627147a8ea47a592c9ad3eb64c2310,

title = "On the benchmarking of ResNet forgery image model using different datasets",

abstract = "This paper presents the benchmarking and improve- ment of the ResNet image forgery model using three different datasets (CASIA, Columbia, and LSBU). The model is based on classification, where forgery images have been edited using cut-paste modification technique.The images are categorized to check if the algorithm can successfully identify the difference between the original and the forgery image. All images have been pre-processed with Gray-Edge detectors to obtain get better classification results. Experimental results have shown that the Gray-edge technique has improved the accuracy across all image datasets.",

keywords = "Image Forgery, LSBU-Columbia-CASIA image datasets, ResNet",

author = "Faria Hossain and Tasos Dagiuklas",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 International Conference on Human-Centered Cognitive Systems, HCCS 2022 ; Conference date: 17-12-2022 Through 18-12-2022",

year = "2022",

month = dec,

day = "18",

doi = "10.1109/HCCS55241.2022.10090275",

language = "English",

series = "Proceedings - 2022 International Conference on Human-Centered Cognitive Systems, HCCS 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "Proceedings - 2022 International Conference on Human-Centered Cognitive Systems, HCCS 2022",

address = "United States",

}

Hossain, F & Dagiuklas, T 2022, On the benchmarking of ResNet forgery image model using different datasets. in Proceedings - 2022 International Conference on Human-Centered Cognitive Systems, HCCS 2022. Proceedings - 2022 International Conference on Human-Centered Cognitive Systems, HCCS 2022, Institute of Electrical and Electronics Engineers Inc., 2022 International Conference on Human-Centered Cognitive Systems, HCCS 2022, Shanghai, China, 17/12/22. https://doi.org/10.1109/HCCS55241.2022.10090275, https://doi.org/10.1109/HCCS55241.2022.10090275

On the benchmarking of ResNet forgery image model using different datasets. / Hossain, Faria ; Dagiuklas, Tasos.
Proceedings - 2022 International Conference on Human-Centered Cognitive Systems, HCCS 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (Proceedings - 2022 International Conference on Human-Centered Cognitive Systems, HCCS 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - On the benchmarking of ResNet forgery image model using different datasets

AU - Hossain, Faria

AU - Dagiuklas, Tasos

PY - 2022/12/18

Y1 - 2022/12/18

N2 - This paper presents the benchmarking and improve- ment of the ResNet image forgery model using three different datasets (CASIA, Columbia, and LSBU). The model is based on classification, where forgery images have been edited using cut-paste modification technique.The images are categorized to check if the algorithm can successfully identify the difference between the original and the forgery image. All images have been pre-processed with Gray-Edge detectors to obtain get better classification results. Experimental results have shown that the Gray-edge technique has improved the accuracy across all image datasets.

AB - This paper presents the benchmarking and improve- ment of the ResNet image forgery model using three different datasets (CASIA, Columbia, and LSBU). The model is based on classification, where forgery images have been edited using cut-paste modification technique.The images are categorized to check if the algorithm can successfully identify the difference between the original and the forgery image. All images have been pre-processed with Gray-Edge detectors to obtain get better classification results. Experimental results have shown that the Gray-edge technique has improved the accuracy across all image datasets.

KW - Image Forgery

KW - LSBU-Columbia-CASIA image datasets

KW - ResNet

UR - https://www.scopus.com/pages/publications/85153684200

U2 - 10.1109/HCCS55241.2022.10090275

DO - 10.1109/HCCS55241.2022.10090275

M3 - Conference contribution

T3 - Proceedings - 2022 International Conference on Human-Centered Cognitive Systems, HCCS 2022

BT - Proceedings - 2022 International Conference on Human-Centered Cognitive Systems, HCCS 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 International Conference on Human-Centered Cognitive Systems, HCCS 2022

Y2 - 17 December 2022 through 18 December 2022

ER -

Hossain F , Dagiuklas T. On the benchmarking of ResNet forgery image model using different datasets. In Proceedings - 2022 International Conference on Human-Centered Cognitive Systems, HCCS 2022. Institute of Electrical and Electronics Engineers Inc. 2022. (Proceedings - 2022 International Conference on Human-Centered Cognitive Systems, HCCS 2022). doi: 10.1109/HCCS55241.2022.10090275, 10.1109/HCCS55241.2022.10090275

On the benchmarking of ResNet forgery image model using different datasets

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Cite this