New Texture Descriptor Based on Modified Fractional Entropy for Digital Image Splicing Forgery Detection.

Hamid Jalab,Nurul Noor,Thamarai Subramaniam,Hasan Kahtan,Rabha Ibrahim

doi:10.3390/e21040371

Abstract

Forgery in digital images is immensely affected by the improvement of image manipulation tools. Image forgery can be classified as image splicing or copy-move on the basis of the image manipulation type. Image splicing involves creating a new tampered image by merging the components of one or more images. Moreover, image splicing disrupts the content and causes abnormality in the features of a tampered image. Most of the proposed algorithms are incapable of accurately classifying high-dimension feature vectors. Thus, the current study focuses on improving the accuracy of image splicing detection with low-dimension feature vectors. This study also proposes an approximated Machado fractional entropy (AMFE) of the discrete wavelet transform (DWT) to effectively capture splicing artifacts inside an image. AMFE is used as a new fractional texture descriptor, while DWT is applied to decompose the input image into a number of sub-images with different frequency bands. The standard image dataset CASIA v2 was used to evaluate the proposed approach. Superior detection accuracy and positive and false positive rates were achieved compared with other state-of-the-art approaches with a low-dimension of feature vectors.

Highlights

Image forgery detection refers to the process of identifying inconsistent regions in an image to authenticate the input digital image [1,2]
We develop a new fractional texture descriptor based on the fractional entropy of the wavelet transform of all none-overlapping image blocks
Numerous splicing detection techniques may be affected by several problems, such as high feature dimensionality and low accuracy with high false positive rates

Summary

Introduction

Image forgery detection refers to the process of identifying inconsistent regions in an image to authenticate the input digital image [1,2]. The detection of image forgery is divided into two types [3,4], namely active and passive authentication. The former depends on digital fingerprint and requires an original input image, whereas the latter is blind and does not require a priori knowledge about the original image. The most recent techniques of passive authentication for splicing forgery detection in digital images have common limitations that are related to the dimension of feature vectors and detection accuracy.

Methods

Results

Conclusion