# Further Study on GFR Features for JPEG Steganalysis

## TL;DR

This paper enhances GFR features for JPEG steganalysis by introducing a histogram merging method based on filter symmetries and a weighted histogram approach, improving detection robustness and sensitivity.

## Contribution

It proposes novel histogram merging and weighted histogram techniques for GFR features, and designs a CNN to optimize residual filter design for JPEG steganalysis.

## Key findings

- Improved GFR features outperform previous methods in detection accuracy.
- The proposed methods increase robustness and sensitivity to residual changes.
- CNN-based detector effectively replicates and enhances GFR-based detection.

## Abstract

The GFR (Gabor Filter Residual) features, built as histograms of quantized residuals obtained with 2D Gabor filters, can achieve competitive detection performance against adaptive JPEG steganography. In this paper, an improved version of the GFR is proposed. First, a novel histogram merging method is proposed according to the symmetries between different Gabor filters, thus making the features more compact and robust. Second, a new weighted histogram method is proposed by considering the position of the residual value in a quantization interval, making the features more sensitive to the slight changes in residual values. The experiments are given to demonstrate the effectiveness of our proposed methods. Finally, we design a CNN to duplicate the detector with the improved GFR features and the ensemble classifier, thus optimizing the design of the filters used to form residuals in JPEG-phase-aware features.