Home > Archive > 2013 > Volume 3 Number 5 (Oct. 2013) >
IJIET 2013 Vol.3(5): 512-515 ISSN: 2010-3689
DOI: 10.7763/IJIET.2013.V3.327

Double JPEG Compression Detection Based on Extended First Digit Features of DCT Coefficients

Wei Hou, Zhe Ji, Xin Jin, and Xing Li

Abstract—Double JPEG compression detection is an important research topic for digital forensics. In this paper, we propose a powerful recompression detection method by extending the first digit features. Based on the analysis of the distribution of the first digits of quantized DCT coefficients, we extract the joint probabilities of the mode based first digits of the quantized DCT coefficients including value zero as the classifying features to distinguish between singly and doubly compressed images. Extensive experiments and comparisons with prior state-of-the-art demonstrate that the proposed scheme can detect the double JPEG compression effectively and outperforms the existing algorithms significantly. Moreover, our method can achieve a satisfactory classification accuracy even for the double JPEG compression with quality factor 95 followed by 50 or 55, while many previous works fail in the detection.

Index Terms—Double compression detection, digital forensics, first digit, JPEG.

Wei Hou, Zhe Ji, and Xin Jin are with the National Computer Network and Information Security Administration Center, 100029, Beijing, China (e-mail: hw@cert.org.cn, jz@cert.org.cn, jinxin@cert.org.cn).
Xing Li is with the National Digital Switching System Engineering and Technological Research Center, 450002, Zhengzhou Henan, China (tel.: +86 371 81632704; e-mail: listarcat@163.com).


Cite:Wei Hou, Zhe Ji, Xin Jin, and Xing Li, "Double JPEG Compression Detection Based on Extended First Digit Features of DCT Coefficients," International Journal of Information and Education Technology vol. 3, no. 5, pp. 512-515, 2013.

General Information

  • ISSN: 2010-3689 (Online)
  • Abbreviated Title: Int. J. Inf. Educ. Technol.
  • Frequency: Monthly
  • DOI: 10.18178/IJIET
  • Editor-in-Chief: Prof. Dr. Steve Thatcher
  • Executive Editor: Ms. Nancy Y. Liu
  • Abstracting/ Indexing: Scopus (CiteScore 2022: 2.0), INSPEC (IET), UGC-CARE List (India), CNKI, EBSCO, Google Scholar
  • E-mail: ijiet@ejournal.net


Article Metrics in Dimensions