Fast Image Identification Methods for JPEG Images with Different Compression Ratios

Fitri ARNIA  Ikue IIZUKA  Masaaki FUJIYOSHI  Hitoshi KIYA  

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E89-A    No.6    pp.1585-1593
Publication Date: 2006/06/01
Online ISSN: 1745-1337
DOI: 10.1093/ietfec/e89-a.6.1585
Print ISSN: 0916-8508
Type of Manuscript: Special Section PAPER (Special Section on Papers Selected from 2005 International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC2005))
image identification,  fast identification,  compression ratio,  image database,  

Full Text: PDF(393.5KB)>>
Buy this Article

Two schemes for fast identification of JPEG coded images are proposed in this paper. The aim is to identify the JPEG images that are generated from the same original image and have equivalent or different compression ratios. Fast identification can be achieved since the schemes work on the quantized Discrete Cosine Transform (DCT) domain. It is not required to inverse the quantization and the DCT. Moreover, only a few coefficients are commonly required for identification. The first approach can avoid identification leakage or false negative (FN), and probably result in a few false positives (FP). The second approach can avoid both FN and FP, with a slightly higher processing time. By combining the two schemes, a faster and a more perfect identification can be achieved, in which FN and FP can be avoided.