New Texture Descriptor Based on Modified Fractional Entropy for Digital Image Splicing Forgery Detection
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 i...
| Prif Awduron: | , , , , |
|---|---|
| Fformat: | Erthygl |
| Cyhoeddwyd: |
MDPI
2019
|
| Pynciau: |
| _version_ | 1825722188939919360 |
|---|---|
| author | Jalab, Hamid Abdullah Subramaniam, Thamarai Ibrahim, Rabha Waell Kahtan, Hasan Noor, Nurul Fazmidar Mohd |
| author_facet | Jalab, Hamid Abdullah Subramaniam, Thamarai Ibrahim, Rabha Waell Kahtan, Hasan Noor, Nurul Fazmidar Mohd |
| author_sort | Jalab, Hamid Abdullah |
| collection | UM |
| description | 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. © 2019 by the authors. |
| first_indexed | 2024-03-06T06:01:51Z |
| format | Article |
| id | um.eprints-24116 |
| institution | Universiti Malaya |
| last_indexed | 2024-03-06T06:01:51Z |
| publishDate | 2019 |
| publisher | MDPI |
| record_format | dspace |
| spelling | um.eprints-241162020-03-26T06:42:16Z http://eprints.um.edu.my/24116/ New Texture Descriptor Based on Modified Fractional Entropy for Digital Image Splicing Forgery Detection Jalab, Hamid Abdullah Subramaniam, Thamarai Ibrahim, Rabha Waell Kahtan, Hasan Noor, Nurul Fazmidar Mohd QA75 Electronic computers. Computer science 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. © 2019 by the authors. MDPI 2019 Article PeerReviewed Jalab, Hamid Abdullah and Subramaniam, Thamarai and Ibrahim, Rabha Waell and Kahtan, Hasan and Noor, Nurul Fazmidar Mohd (2019) New Texture Descriptor Based on Modified Fractional Entropy for Digital Image Splicing Forgery Detection. Entropy, 21 (4). p. 371. ISSN 1099-4300, DOI https://doi.org/10.3390/e21040371 <https://doi.org/10.3390/e21040371>. https://doi.org/10.3390/e21040371 doi:10.3390/e21040371 |
| spellingShingle | QA75 Electronic computers. Computer science Jalab, Hamid Abdullah Subramaniam, Thamarai Ibrahim, Rabha Waell Kahtan, Hasan Noor, Nurul Fazmidar Mohd New Texture Descriptor Based on Modified Fractional Entropy for Digital Image Splicing Forgery Detection |
| title | New Texture Descriptor Based on Modified Fractional Entropy for Digital Image Splicing Forgery Detection |
| title_full | New Texture Descriptor Based on Modified Fractional Entropy for Digital Image Splicing Forgery Detection |
| title_fullStr | New Texture Descriptor Based on Modified Fractional Entropy for Digital Image Splicing Forgery Detection |
| title_full_unstemmed | New Texture Descriptor Based on Modified Fractional Entropy for Digital Image Splicing Forgery Detection |
| title_short | New Texture Descriptor Based on Modified Fractional Entropy for Digital Image Splicing Forgery Detection |
| title_sort | new texture descriptor based on modified fractional entropy for digital image splicing forgery detection |
| topic | QA75 Electronic computers. Computer science |
| work_keys_str_mv | AT jalabhamidabdullah newtexturedescriptorbasedonmodifiedfractionalentropyfordigitalimagesplicingforgerydetection AT subramaniamthamarai newtexturedescriptorbasedonmodifiedfractionalentropyfordigitalimagesplicingforgerydetection AT ibrahimrabhawaell newtexturedescriptorbasedonmodifiedfractionalentropyfordigitalimagesplicingforgerydetection AT kahtanhasan newtexturedescriptorbasedonmodifiedfractionalentropyfordigitalimagesplicingforgerydetection AT noornurulfazmidarmohd newtexturedescriptorbasedonmodifiedfractionalentropyfordigitalimagesplicingforgerydetection |