JPEG image resampling tampering identification method, device and computer equipment

Abstract

The invention relates to a JPEG image resampling tampering identification method, a JPEG image resampling tampering identification device, a computer device and a computer readable storage medium. Themethod comprises: after a JPEG image is converted into a grayscale image, acquiring a JPEG non-pure color block of the JPEG image, and filtering the JPEG non-pure color block to eliminate JPEG quantization noise in the JPEG image so as to obtain a new JPEG image; dividing the new JPEG image into a plurality of sub-images, obtaining a resampling frequency spectrum of each sub-image, and calculating a resampling factor estimation value of each sub-image according to the resampling frequency spectrum; and performing resampling factor interval estimation according to the resampling factor estimation value of each sub-image, and determining whether the JPEG image is subjected to resampling tampering or not according to an estimation result. According to the method, the problem that the JPEG block effect affects resampling detection is solved through deblocking effect filtering, interference of large-area smooth blocks on estimation is effectively avoided by limiting the range of the regionof interest in the process of estimating the resampling period, and the tampering detection effect of the JPEG image is improved.

Description

technical field [0001] The present application relates to the technical field of image detection, in particular to a JPEG image resampling tampering identification method, a JPEG image resampling tampering identification device, computer equipment and a computer-readable storage medium. Background technique [0002] A digital image is an image obtained by digitizing an analog image, with pixels as the basic element, and can be stored and processed by a digital computer or digital circuit. In recent years, digital images have become the most commonly used information medium in people's daily life. With the popularity of image editing software such as Photoshop (PS), image tampering has become very easy. Although the tampered pictures widely disseminated on the Internet are mostly used for entertainment and have little impact, in professional fields such as justice, medicine, journalism, and publishing, the authenticity and integrity of images need to be absolutely guaranteed;...

AI Technical Summary

Problems solved by technology

As a lossy compression format, JPEG’s Discrete Cosine Transform (DCT) process will also introduce periodic noise, so the noise can also be misidentified by the resampling detection method; therefore, according to the existing Resampling forensics methods cannot distinguish between JPEG quantization noise and resampled signals, resulting in ineffective forensics and tamper detection for JPEG images

Images