Detecting Double Jpeg Compression with Same Quantization Matrix Based on Dense Cnn Feature

Detection of double JPEG compression with same quantization matrix has been regarded as a challenging task in digital image forensics because there are very few modification cues in the tampered images especially when the compression quality factor is low. In order to solve this problem, a comprehensive feature representation based on the dense CNN framework is proposed, which is sensitive to the artifacts caused by double JPEG compression and is not related to the image content. With the appropriate network design and contributing to the characteristics of average pooling, dense connection and transition, the proposed network can differentiate double JPEG compression artifacts accurately. Experiment results on the two datasets have demonstrated that the proposed feature outperforms several state-of-the-art approaches investigated.

1. Introduction

Nowadays, the authenticity and integrity of a digital image can hardly be determined visually due to the powerful and sophisticated image edition tools, which makes digital image forensics more important. Since JPEG is the most widely used format in image communication and storage, double JPEG compression (DJPEG in short) detection has become an important branch in image forensics. Such kind of approaches assume that the original image is usually JPEG compressed once in the imaging stage and the modified image usually undergoes at least two JPEG compressions.