The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Sekiranya imej dikongsi melalui perkhidmatan rangkaian sosial (SNS) dan perkhidmatan storan foto awan (CPSS), diketahui bahawa imej JPEG yang dimuat naik ke perkhidmatan kebanyakannya dimampatkan semula oleh pembekal. Oleh kerana keadaan sedemikian, skema pengenalan imej baharu untuk imej JPEG termampat dua kali dicadangkan dalam kertas ini. Matlamatnya adalah untuk mengesan imej termampat tunggal yang mempunyai imej asal yang sama dengan imej termampat dua kali. Dalam skim yang dicadangkan, ciri yang diekstrak daripada hanya pekali DC dalam pekali DCT digunakan untuk pengenalpastian. Penggunaan ciri ini membolehkan kami bukan sahaja mengelak ralat yang disebabkan oleh pemampatan dua kali tetapi juga untuk melakukan pengenalan untuk imej saiz yang berbeza. Keputusan simulasi menunjukkan keberkesanan yang dicadangkan dari segi prestasi pertanyaan.
Kenta IIDA
Tokyo Metropolitan University
Hitoshi KIYA
Tokyo Metropolitan University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Kenta IIDA, Hitoshi KIYA, "Robust Image Identification with DC Coefficients for Double-Compressed JPEG Images" in IEICE TRANSACTIONS on Information,
vol. E102-D, no. 1, pp. 2-10, January 2019, doi: 10.1587/transinf.2018MUP0007.
Abstract: In the case that images are shared via social networking services (SNS) and cloud photo storage services (CPSS), it is known that the JPEG images uploaded to the services are mostly re-compressed by the providers. Because of such a situation, a new image identification scheme for double-compressed JPEG images is proposed in this paper. The aim is to detect a single-compressed image that has the same original image as the double-compressed ones. In the proposed scheme, a feature extracted from only DC coefficients in DCT coefficients is used for the identification. The use of the feature allows us not only to robustly avoid errors caused by double-compression but also to perform the identification for different size images. The simulation results demonstrate the effectiveness of the proposed one in terms of the querying performance.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2018MUP0007/_p
Salinan
@ARTICLE{e102-d_1_2,
author={Kenta IIDA, Hitoshi KIYA, },
journal={IEICE TRANSACTIONS on Information},
title={Robust Image Identification with DC Coefficients for Double-Compressed JPEG Images},
year={2019},
volume={E102-D},
number={1},
pages={2-10},
abstract={In the case that images are shared via social networking services (SNS) and cloud photo storage services (CPSS), it is known that the JPEG images uploaded to the services are mostly re-compressed by the providers. Because of such a situation, a new image identification scheme for double-compressed JPEG images is proposed in this paper. The aim is to detect a single-compressed image that has the same original image as the double-compressed ones. In the proposed scheme, a feature extracted from only DC coefficients in DCT coefficients is used for the identification. The use of the feature allows us not only to robustly avoid errors caused by double-compression but also to perform the identification for different size images. The simulation results demonstrate the effectiveness of the proposed one in terms of the querying performance.},
keywords={},
doi={10.1587/transinf.2018MUP0007},
ISSN={1745-1361},
month={January},}
Salinan
TY - JOUR
TI - Robust Image Identification with DC Coefficients for Double-Compressed JPEG Images
T2 - IEICE TRANSACTIONS on Information
SP - 2
EP - 10
AU - Kenta IIDA
AU - Hitoshi KIYA
PY - 2019
DO - 10.1587/transinf.2018MUP0007
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2019
AB - In the case that images are shared via social networking services (SNS) and cloud photo storage services (CPSS), it is known that the JPEG images uploaded to the services are mostly re-compressed by the providers. Because of such a situation, a new image identification scheme for double-compressed JPEG images is proposed in this paper. The aim is to detect a single-compressed image that has the same original image as the double-compressed ones. In the proposed scheme, a feature extracted from only DC coefficients in DCT coefficients is used for the identification. The use of the feature allows us not only to robustly avoid errors caused by double-compression but also to perform the identification for different size images. The simulation results demonstrate the effectiveness of the proposed one in terms of the querying performance.
ER -