We propose a method to retrieve similar and duplicate images from a JPEG (Joint Photographic Image Group) image database. Similarity level is decided based on the DCT (Discrete Cosine Transform) coefficients signs. The method is simple and fast because it uses the DCT coefficients signs as features, which can be obtained directly after partial decoding of JPEG bitstream. The method is robust to JPEG compression, in which similarity level of duplicate images, i.e., images that are compressed from the same original images with different compression ratios, is not disguised due to JPEG compression. Simulation results showed the superiority of the method compared to previous methods in terms of computational complexity and robustness to JPEG compression.
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.
Copy
Fitri ARNIA, Ikue IIZUKA, Masaaki FUJIYOSHI, Hitoshi KIYA, "DCT Sign-Based Similarity Measure for JPEG Image Retrieval" in IEICE TRANSACTIONS on Fundamentals,
vol. E90-A, no. 9, pp. 1976-1985, September 2007, doi: 10.1093/ietfec/e90-a.9.1976.
Abstract: We propose a method to retrieve similar and duplicate images from a JPEG (Joint Photographic Image Group) image database. Similarity level is decided based on the DCT (Discrete Cosine Transform) coefficients signs. The method is simple and fast because it uses the DCT coefficients signs as features, which can be obtained directly after partial decoding of JPEG bitstream. The method is robust to JPEG compression, in which similarity level of duplicate images, i.e., images that are compressed from the same original images with different compression ratios, is not disguised due to JPEG compression. Simulation results showed the superiority of the method compared to previous methods in terms of computational complexity and robustness to JPEG compression.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1093/ietfec/e90-a.9.1976/_p
Copy
@ARTICLE{e90-a_9_1976,
author={Fitri ARNIA, Ikue IIZUKA, Masaaki FUJIYOSHI, Hitoshi KIYA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={DCT Sign-Based Similarity Measure for JPEG Image Retrieval},
year={2007},
volume={E90-A},
number={9},
pages={1976-1985},
abstract={We propose a method to retrieve similar and duplicate images from a JPEG (Joint Photographic Image Group) image database. Similarity level is decided based on the DCT (Discrete Cosine Transform) coefficients signs. The method is simple and fast because it uses the DCT coefficients signs as features, which can be obtained directly after partial decoding of JPEG bitstream. The method is robust to JPEG compression, in which similarity level of duplicate images, i.e., images that are compressed from the same original images with different compression ratios, is not disguised due to JPEG compression. Simulation results showed the superiority of the method compared to previous methods in terms of computational complexity and robustness to JPEG compression.},
keywords={},
doi={10.1093/ietfec/e90-a.9.1976},
ISSN={1745-1337},
month={September},}
Copy
TY - JOUR
TI - DCT Sign-Based Similarity Measure for JPEG Image Retrieval
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1976
EP - 1985
AU - Fitri ARNIA
AU - Ikue IIZUKA
AU - Masaaki FUJIYOSHI
AU - Hitoshi KIYA
PY - 2007
DO - 10.1093/ietfec/e90-a.9.1976
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E90-A
IS - 9
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - September 2007
AB - We propose a method to retrieve similar and duplicate images from a JPEG (Joint Photographic Image Group) image database. Similarity level is decided based on the DCT (Discrete Cosine Transform) coefficients signs. The method is simple and fast because it uses the DCT coefficients signs as features, which can be obtained directly after partial decoding of JPEG bitstream. The method is robust to JPEG compression, in which similarity level of duplicate images, i.e., images that are compressed from the same original images with different compression ratios, is not disguised due to JPEG compression. Simulation results showed the superiority of the method compared to previous methods in terms of computational complexity and robustness to JPEG compression.
ER -