Forgery Detection Based on Quantization Table Estimation in JPEG Compressed Digital Images

Rodrigues, Anisha P and Bijur, Gururaj (2011) Forgery Detection Based on Quantization Table Estimation in JPEG Compressed Digital Images. In: International Conference on Emerging Trends in Engineering, 15 and 16 May 2013, NITTE Karnataka.

[img] PDF
1-ICETE12-CS151-Forgery Detection Based on Quantization Table Estimation in JPEG Compressed Digital Images.pdf - Published Version
Restricted to Registered users only

Download (643kB) | Request a copy

Abstract

Digital images can be forged easily with today’s widely available image processing software. In this paper, we propose passive approach to detect digital forgeries. The scheme is composed of quantization table estimation, prescreening, candidate region selection and forgery detection. Most image acquisition and editing tools use JPEG standard for image compression. The histogram of Discrete Cosine Transform (DCT) coefficients contains information on the compression parameters for JPEG. To estimate the quantization table, we present a peak detection method to estimate the quantization table from the peaks of the histogram of DCT coefficients. After quantization table estimation, the variation resulting from the inconsistent of quantization table is utilized to detect tampered regions. We used the common forgery techniques like copy-paste tampering and inpainting to evaluate scheme performance in tampering detection. We tested the scheme on a set of images which gave an average estimation accuracy of 81% for jpeg images with different quality factor.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Tampering, DCT, Quantization, JPEG, EDS, Q.
Subjects: Engineering > MIT Manipal > Computer Science and Engineering
Depositing User: MIT Library
Date Deposited: 10 Jan 2014 06:32
Last Modified: 10 Jan 2014 06:32
URI: http://eprints.manipal.edu/id/eprint/138303

Actions (login required)

View Item View Item