Deep Convolutional Neural Network for Identifying Seam-Carving Forgery

TL;DR

This paper introduces a CNN-based method for detecting and localizing seam-carving image forgeries, achieving state-of-the-art accuracy and robustness in classifying original, seam-inserted, and seam-removed images.

Contribution

The paper presents a novel CNN architecture with specialized blocks and an ensemble module for effective seam carving forgery detection and localization.

Findings

State-of-the-art classification accuracy for three-class seam carving detection.

Robust performance on unseen cases and localizing seam modifications.

Effective detection of both seam-inserted and seam-removed regions.

Abstract

Seam carving is a representative content-aware image retargeting approach to adjust the size of an image while preserving its visually prominent content. To maintain visually important content, seam-carving algorithms first calculate the connected path of pixels, referred to as the seam, according to a defined cost function and then adjust the size of an image by removing and duplicating repeatedly calculated seams. Seam carving is actively exploited to overcome diversity in the resolution of images between applications and devices; hence, detecting the distortion caused by seam carving has become important in image forensics. In this paper, we propose a convolutional neural network (CNN)-based approach to classifying seam-carving-based image retargeting for reduction and expansion. To attain the ability to learn low-level features, we designed a CNN architecture comprising five types of network blocks specialized for capturing subtle signals. An ensemble module is further adopted to both enhance performance and comprehensively analyze the features in the local areas of the given image. To validate the effectiveness of our work, extensive experiments based on various CNN-based baselines were conducted. Compared to the baselines, our work exhibits state-of-the-art performance in terms of three-class classification (original, seam inserted, and seam removed). In addition, our model with the ensemble module is robust for various unseen cases. The experimental results also demonstrate that our method can be applied to localize both seam-removed and seam-inserted areas.