Detection and Classification of Various Image Operations Using Deep Learning Technology

Tian Huang; Xiaochen Yuan

doi:10.1109/ICMLC.2018.8526999

Detection and Classification of Various Image Operations Using Deep Learning Technology

Tian Huang, Xiaochen Yuan

Macau University of Science and Technology

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

7 Citations (Scopus)

Abstract

As one of the main medium for information transmission, the digital imagecan be easily tampered during transmission. It is becoming more and more important to identifywhether the given image is an original image or a processed image. In this paper, we propose acompact universal feature based on spatial domain in virtue of some latest image forensic methods and design a multi-class classification scheme using the deep learning technique, to identify and furthermore classify the various normal image operations. According to the experimental results, the proposed method can well detect and classify the multiple common image post-processing operations. And the comparison with the existing feature shows the better performance of the proposed method.

Original language	English
Title of host publication	Proceedings of 2018 International Conference on Machine Learning and Cybernetics, ICMLC 2018
Publisher	IEEE Computer Society
Pages	50-55
Number of pages	6
ISBN (Electronic)	9781538652121
DOIs	https://doi.org/10.1109/ICMLC.2018.8526999
Publication status	Published - 7 Nov 2018
Externally published	Yes
Event	17th International Conference on Machine Learning and Cybernetics, ICMLC 2018 - Chengdu, China Duration: 15 Jul 2018 → 18 Jul 2018

Publication series

Name	Proceedings - International Conference on Machine Learning and Cybernetics
Volume	1
ISSN (Print)	2160-133X
ISSN (Electronic)	2160-1348

Conference

Conference	17th International Conference on Machine Learning and Cybernetics, ICMLC 2018
Country/Territory	China
City	Chengdu
Period	15/07/18 → 18/07/18

Keywords

Convolutional neural network (CNN)
Deep learning technique
Image post-processing Operations detection
Spatial rich model (SRM)

Access to Document

10.1109/ICMLC.2018.8526999

Cite this

Huang, T., & Yuan, X. (2018). Detection and Classification of Various Image Operations Using Deep Learning Technology. In Proceedings of 2018 International Conference on Machine Learning and Cybernetics, ICMLC 2018 (pp. 50-55). Article 8526999 (Proceedings - International Conference on Machine Learning and Cybernetics; Vol. 1). IEEE Computer Society. https://doi.org/10.1109/ICMLC.2018.8526999

@inproceedings{c71d6cee66f84d53abf239171dd3cd07,

title = "Detection and Classification of Various Image Operations Using Deep Learning Technology",

abstract = "As one of the main medium for information transmission, the digital imagecan be easily tampered during transmission. It is becoming more and more important to identifywhether the given image is an original image or a processed image. In this paper, we propose acompact universal feature based on spatial domain in virtue of some latest image forensic methods and design a multi-class classification scheme using the deep learning technique, to identify and furthermore classify the various normal image operations. According to the experimental results, the proposed method can well detect and classify the multiple common image post-processing operations. And the comparison with the existing feature shows the better performance of the proposed method.",

keywords = "Convolutional neural network (CNN), Deep learning technique, Image post-processing Operations detection, Spatial rich model (SRM)",

author = "Tian Huang and Xiaochen Yuan",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 17th International Conference on Machine Learning and Cybernetics, ICMLC 2018 ; Conference date: 15-07-2018 Through 18-07-2018",

year = "2018",

month = nov,

day = "7",

doi = "10.1109/ICMLC.2018.8526999",

language = "English",

series = "Proceedings - International Conference on Machine Learning and Cybernetics",

publisher = "IEEE Computer Society",

pages = "50--55",

booktitle = "Proceedings of 2018 International Conference on Machine Learning and Cybernetics, ICMLC 2018",

address = "United States",

}

Huang, T & Yuan, X 2018, Detection and Classification of Various Image Operations Using Deep Learning Technology. in Proceedings of 2018 International Conference on Machine Learning and Cybernetics, ICMLC 2018., 8526999, Proceedings - International Conference on Machine Learning and Cybernetics, vol. 1, IEEE Computer Society, pp. 50-55, 17th International Conference on Machine Learning and Cybernetics, ICMLC 2018, Chengdu, China, 15/07/18. https://doi.org/10.1109/ICMLC.2018.8526999

Detection and Classification of Various Image Operations Using Deep Learning Technology. / Huang, Tian; Yuan, Xiaochen.
Proceedings of 2018 International Conference on Machine Learning and Cybernetics, ICMLC 2018. IEEE Computer Society, 2018. p. 50-55 8526999 (Proceedings - International Conference on Machine Learning and Cybernetics; Vol. 1).

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

TY - GEN

T1 - Detection and Classification of Various Image Operations Using Deep Learning Technology

AU - Huang, Tian

AU - Yuan, Xiaochen

PY - 2018/11/7

Y1 - 2018/11/7

N2 - As one of the main medium for information transmission, the digital imagecan be easily tampered during transmission. It is becoming more and more important to identifywhether the given image is an original image or a processed image. In this paper, we propose acompact universal feature based on spatial domain in virtue of some latest image forensic methods and design a multi-class classification scheme using the deep learning technique, to identify and furthermore classify the various normal image operations. According to the experimental results, the proposed method can well detect and classify the multiple common image post-processing operations. And the comparison with the existing feature shows the better performance of the proposed method.

AB - As one of the main medium for information transmission, the digital imagecan be easily tampered during transmission. It is becoming more and more important to identifywhether the given image is an original image or a processed image. In this paper, we propose acompact universal feature based on spatial domain in virtue of some latest image forensic methods and design a multi-class classification scheme using the deep learning technique, to identify and furthermore classify the various normal image operations. According to the experimental results, the proposed method can well detect and classify the multiple common image post-processing operations. And the comparison with the existing feature shows the better performance of the proposed method.

KW - Convolutional neural network (CNN)

KW - Deep learning technique

KW - Image post-processing Operations detection

KW - Spatial rich model (SRM)

UR - http://www.scopus.com/inward/record.url?scp=85058041256&partnerID=8YFLogxK

U2 - 10.1109/ICMLC.2018.8526999

DO - 10.1109/ICMLC.2018.8526999

M3 - Conference contribution

AN - SCOPUS:85058041256

T3 - Proceedings - International Conference on Machine Learning and Cybernetics

SP - 50

EP - 55

BT - Proceedings of 2018 International Conference on Machine Learning and Cybernetics, ICMLC 2018

PB - IEEE Computer Society

T2 - 17th International Conference on Machine Learning and Cybernetics, ICMLC 2018

Y2 - 15 July 2018 through 18 July 2018

ER -

Detection and Classification of Various Image Operations Using Deep Learning Technology

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this