Robust median filtering detection based on filtered residual

摘要: In multimedia forensics, exposing an image's processing history draws much attention. Median filtering is a popular noise removal tool, which has been used as anti-forensics tool recently. An image usually saved in compressed format such the JPEG format. While detection of median from difficult because typical filter characteristics are suppressed by quantization and block artifacts. this paper, we introduce novel forensic trace --- residual. first applied on test image, difference between initial filtered output called The residual fingerprint. Thus, interference edge texture regarded major limitation existing methods can be reduced. Experimental results large database show that proposed method very robust to post- compression, achieves better performance than state-of-the-art works.