Robust Image Identification without Visible Information for JPEG Images

Kenta IIDA; Hitoshi KIYA

doi:10.1587/transinf.2017MUP0005

Robust Image Identification without Visible Information for JPEG Images

Kenta IIDA, Hitoshi KIYA

Full Text Views

0

Share
Cite this

Summary :

A robust identification scheme for JPEG images is proposed in this paper. The aim is to robustly identify JPEG images that are generated from the same original image, under various compression conditions such as differences in compression ratios and initial quantization matrices. The proposed scheme does not provide any false negative matches in principle. In addition, secure features, which do not have any visual information, are used to achieve not only a robust identification scheme but also secure one. Conventional schemes can not avoid providing false negative matches under some compression conditions, and are required to manage a secret key for secure identification. The proposed scheme is applicable to the uploading process of images on social networks like Twitter for image retrieval and forensics. A number of experiments are carried out to demonstrate that the effectiveness of the proposed method. The proposed method outperforms conventional ones in terms of query performances, while keeping a reasonable security level.

Publication: IEICE TRANSACTIONS on Information Vol.E101-D No.1 pp.13-19

Publication Date: 2018/01/01

Publicized: 2017/10/16

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2017MUP0005

Type of Manuscript: Special Section PAPER (Special Section on Enriched Multimedia — Potential and Possibility of Multimedia Contents for the Future —)

Category

Authors

Kenta IIDA
Tokyo Metropolitan University
Hitoshi KIYA
Tokyo Metropolitan University

Keyword

image identification, JPEG, social networks

Cite this

Copy

Kenta IIDA, Hitoshi KIYA, "Robust Image Identification without Visible Information for JPEG Images" in IEICE TRANSACTIONS on Information, vol. E101-D, no. 1, pp. 13-19, January 2018, doi: 10.1587/transinf.2017MUP0005.
Abstract: A robust identification scheme for JPEG images is proposed in this paper. The aim is to robustly identify JPEG images that are generated from the same original image, under various compression conditions such as differences in compression ratios and initial quantization matrices. The proposed scheme does not provide any false negative matches in principle. In addition, secure features, which do not have any visual information, are used to achieve not only a robust identification scheme but also secure one. Conventional schemes can not avoid providing false negative matches under some compression conditions, and are required to manage a secret key for secure identification. The proposed scheme is applicable to the uploading process of images on social networks like Twitter for image retrieval and forensics. A number of experiments are carried out to demonstrate that the effectiveness of the proposed method. The proposed method outperforms conventional ones in terms of query performances, while keeping a reasonable security level.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.2017MUP0005/_p

Copy

@ARTICLE{e101-d_1_13,
author={Kenta IIDA, Hitoshi KIYA, },
journal={IEICE TRANSACTIONS on Information},
title={Robust Image Identification without Visible Information for JPEG Images},
year={2018},
volume={E101-D},
number={1},
pages={13-19},
abstract={A robust identification scheme for JPEG images is proposed in this paper. The aim is to robustly identify JPEG images that are generated from the same original image, under various compression conditions such as differences in compression ratios and initial quantization matrices. The proposed scheme does not provide any false negative matches in principle. In addition, secure features, which do not have any visual information, are used to achieve not only a robust identification scheme but also secure one. Conventional schemes can not avoid providing false negative matches under some compression conditions, and are required to manage a secret key for secure identification. The proposed scheme is applicable to the uploading process of images on social networks like Twitter for image retrieval and forensics. A number of experiments are carried out to demonstrate that the effectiveness of the proposed method. The proposed method outperforms conventional ones in terms of query performances, while keeping a reasonable security level.},
keywords={},
doi={10.1587/transinf.2017MUP0005},
ISSN={1745-1361},
month={January},}

Copy

TY - JOUR
TI - Robust Image Identification without Visible Information for JPEG Images
T2 - IEICE TRANSACTIONS on Information
SP - 13
EP - 19
AU - Kenta IIDA
AU - Hitoshi KIYA
PY - 2018
DO - 10.1587/transinf.2017MUP0005
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E101-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2018
AB - A robust identification scheme for JPEG images is proposed in this paper. The aim is to robustly identify JPEG images that are generated from the same original image, under various compression conditions such as differences in compression ratios and initial quantization matrices. The proposed scheme does not provide any false negative matches in principle. In addition, secure features, which do not have any visual information, are used to achieve not only a robust identification scheme but also secure one. Conventional schemes can not avoid providing false negative matches under some compression conditions, and are required to manage a secret key for secure identification. The proposed scheme is applicable to the uploading process of images on social networks like Twitter for image retrieval and forensics. A number of experiments are carried out to demonstrate that the effectiveness of the proposed method. The proposed method outperforms conventional ones in terms of query performances, while keeping a reasonable security level.
ER -