A Machine Learning Method for Detecting the Trace of Seam Carving

Zehra Karapinar Senturk,Devrim Akgun

doi:10.5755/j02.eie.29050

Zehra Karapinar Senturk, Devrim Akgun

Open Access

https://doi.org/10.5755/j02.eie.29050

Copy DOI

Abstract

Image retargeting is a manipulation approach for resizing the images while aiming to keep the image distortion at a low level. Detecting image retargeting is of importance in image forensics or sometimes of importance in checking the originality. The aim of this paper is to introduce a new blind detection method for identifying retargeted images based on seam carving. For this purpose, a new method based on stripes at various numbers, Local Binary Pattern (LBP) transform, and energy map is introduced. The sub-images were obtained from square root of the energy map of LBP transform in the form of stripes for the feature extraction and these were evaluated in terms of several statistical features. The features extracted both from the natural and the seam carved images were used to train a Support Vector Machine (SVM) as a binary classifier. Experimental results were obtained using four-fold cross validation to improve the validity of the results during the evaluation process. According to the experiments, the proposed method produces improved accuracies when compared with the state-of-the-art solutions for the image retargeting detection based on seam carving.

Highlights

Digital image forensics is attracting increasing interest as image manipulation methods continue to be developed
The grid search method was used to find the optimal parameters of the radial basis function (RBF)
Detection accuracy is very sensitive to the c (Cost) and g (Gamma) of the RBF; the best c and g were selected from the results of the grid search for better classification performance

Summary

Introduction

Digital image forensics is attracting increasing interest as image manipulation methods continue to be developed. Its success comes from evaluating the images in a semantic manner It considers the energy maps (maps with edges, salient objects, user-specified regions, etc.) of the images and adds or removes the least important pixel path without causing visual deterioration. Seam Carving Algorithm Seam carving [21] is a content-aware image retargeting technique that can be used for different purposes, including image resizing [22]–[28], image enhancement [29], and object removal. In this method, an optimal seam is found and removed or inserted one by one until the desired image size or other stopping conditions are satisfied. Pixels (Is) that form the seam (s) path can be described as

Objectives

Results

Conclusion