Texture-characteristic-based method for passively and blindly obtaining evidence of digital image

Abstract

The invention discloses a texture-characteristic-based method for passively and blindly obtaining the evidence of a digital image. The method is characterized in that the image content is expressed by selecting six texture characteristic quantities, namely the image texture mean value, the texture standard deviation, the texture smoothness, the texture third moment, the texture consistency and the texture entropy. Compared with the existing method for expressing the information of the image content by selecting the indirect characteristic quantity of an image transform domain, the method is used for expressing the image information by directly selecting the texture characteristic of the image, so that the information of the image can be more adequately expressed; and compared with the existing method, the method can be used for reducing the dimensionality of the characteristic quantity, and the texture characteristic selected by the method has the characteristics of layer property, dimensional property, translation invariance and the like, so that the image falsifying and evidence obtaining detection rate and the robustness can be improved, and the method is applicable to the fields of identification on the content truth of images and the like.

Description

Technical field [0001] The invention belongs to the technical field of signal and information processing, and specifically relates to a passive blind forensics method based on texture features for copy-paste tampering in image forgery. Background technique [0002] The advent of the digital age has not only brought people enjoy advanced visual effects, but also enabled some criminals to spread forged and tampered images through the Internet and other media, which has a negative impact on individuals and society. Therefore, the digital age has become a "double-edged sword" while making it convenient for people. Digital image copy-paste tampering is one of the most common image forgery methods, which can generally be divided into two categories: one is copy-paste tampering of the same image; the other is copy-paste between different images Falsify forgery. [0003] The existing methods for copy-paste tampering forensics of the same image include: [0004] In the 2004 Dartmouth Unive...

AI Technical Summary

Problems solved by technology

[0004] In 2004, a digital image copy-paste passive blind forensics method based on Principal Component Analysis (PCA) was proposed at the Computer Science and Technology Report Conference of Dartmouth University in the United States. It uses image transformation domain feature quantities to represent image content. The defect of poor robustness

[0005] The copy-paste tampering passive blind forensics method based on discrete cosine transform (DCT) coefficients proposed in the Proceedings of the International Conference on Information Processing of the Institute of Electrical and Electronics Engineering (IEEE) held in 2005, volume 53, phase 2, pages 758-767, although Realized the forensics of image copy-paste tampering, but it has the disadvantage of large amount of calculation

[0006] In 2007, the Proceedings of the International Conference on Multimedia Information and Forensics of the Institute of Electrical and Electronics Engineering (IEEE) held in 2007, on pages 1750-1753 of the third issue, proposed a passive blind forensics method based on wavelet and singular value decomposition for image duplication and forgery areas. The amount of calculation of the method, but it is still not possible to quickly obtain evidence for larger images in practice

[0007] A digital image copy-paste tampering passive blind forensics method based on the master transfer vector mentioned in the Chinese Journal of Computer Science, Vol.

[0008] In 2011, China's "Computer Application" Volume 31, Issue 6, pages 1621-1630, proposed a method based on gray-level co-occurrence moments for copying and tampering of image areas, which has the defects of large amount of calculation and poor robustness.

Images