Image Processing Operations Identification via Convolutional Neural Network

TL;DR

This paper introduces a CNN-based approach for identifying various image processing operations, outperforming existing hand-crafted feature methods and achieving state-of-the-art results in image forensics.

Contribution

It proposes a novel CNN architecture with specialized components for adaptive feature learning in image forensics, handling multiple operations simultaneously.

Findings

Outperforms existing methods based on hand-crafted features.

Achieves state-of-the-art results in identifying image processing operations.

Demonstrates robustness and rationality of the proposed CNN model.

Abstract

In recent years, image forensics has attracted more and more attention, and many forensic methods have been proposed for identifying image processing operations. Up to now, most existing methods are based on hand crafted features, and just one specific operation is considered in their methods. In many forensic scenarios, however, multiple classification for various image processing operations is more practical. Besides, it is difficult to obtain effective features by hand for some image processing operations. In this paper, therefore, we propose a new convolutional neural network (CNN) based method to adaptively learn discriminative features for identifying typical image processing operations. We carefully design the high pass filter bank to get the image residuals of the input image, the channel expansion layer to mix up the resulting residuals, the pooling layers, and the activation functions employed in our method. The extensive results show that the proposed method can outperform the currently best method based on hand crafted features and three related methods based on CNN for image steganalysis and/or forensics, achieving the state-of-the-art results. Furthermore, we provide more supplementary results to show the rationality and robustness of the proposed model.