Detection of digital photomontage based on image contrast analysis

DOI: 10.31673/2409-7292.2020.024751

Abstract

Details that are invisible to the human eye in an image with low contrast can become an indicator of inconsistencies in the relative position of objects / people in the image or their illumination, which can be considered a sign of digital tampering. The article proposes a new approach for detecting photomontage in a digital image only using methods to increase the contrast of the image.

Key words: digital image, photomontage, digital image illumination, digital image contrast.

References
1. Popescu A. C. and Farid H. Statistical Tools for Digital Forensic. Department of Compute Science at Dartmouth College Information Hiding.-2004.-p.128-147.
2. Lukas J. and Fridrich J. Estimation of Primary Quantization Matrix in Double Compressed JPEG Images. Proc. Of DFRWS 2003, Cleveland, OH, August 5-8. Department of Electrical and Computer Engineering SUNY Binghamton, Binghamton, NY 13902-6000.
3. He J., Lin Z., Wang L. and Tang X. Detecting JPEG Images Via DCT Coefficient Analysis/ECCV(3) 2006: 423-435.
4. Johnson M. K. and Farid H. Exposing Digital Forgeries by Detecting Inconsistencies in Lighting. ACM Multimedia and Security Workshop. New York, 2005, p. 1-10.
5. Lukas J., Fridrich J. and Goljan M. Detecting Digital Image Forgeries Using Sensor Pattern Noise. Department of Electrical and Computer Engineering SUNY Binghamton, Binghamton, NY 13902-6000.
6. Гонсалес Р., Вудс Р. Цифровая обработка изображений.- М.: Техносфера, 2005.- 1072с.