Image splicing forgery detection based on low-dimensional singular value decomposition of discrete cosine transform coefficients
Digital image forgery has significantly increased due to the rapid development of several tools of image manipulation. Based on the manipulation used to produce a tampered image, image forgery techniques can be characterized into three types: copy–move forgery, image splicing, and image retouching....
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Published: |
Springer Verlag (Germany)
2019
|
| Subjects: |
| _version_ | 1825722169966985216 |
|---|---|
| author | Moghaddasi, Zahra Jalab, Hamid Abdullah Noor, Rafidah Md |
| author_facet | Moghaddasi, Zahra Jalab, Hamid Abdullah Noor, Rafidah Md |
| author_sort | Moghaddasi, Zahra |
| collection | UM |
| description | Digital image forgery has significantly increased due to the rapid development of several tools of image manipulation. Based on the manipulation used to produce a tampered image, image forgery techniques can be characterized into three types: copy–move forgery, image splicing, and image retouching. Image splicing is achieved by adding regions from one image into another. This technique changes the content of the target image and causes variations in image features which are used to detect the forgery regions. In this study, an image splicing forgery detection method based on low-dimensional singular value decomposition of discrete cosine transform (DCT) coefficients has been presented. The suspicious input image is divided into multi-size blocks, and each block is transformed into 2D DCT. The DCT coefficients are calculated correspondingly to each block. The features from DCT are extracted using SVD algorithm. The roughness measure is calculated for the set of singular values obtained. Lastly, four types of statistical features—mean, variance, third-order moment skewness, and fourth-order moment kurtosis—are extracted from SVD features and are then arranged in a feature vector. Feature reduction has been applied by kernel principal component analysis. Finally, support vector machine is used to distinguish between the authenticated and spliced images. The proposed method was evaluated against three standard image datasets CASIA v1, DVMM v1, and DVMM v2. The proposed method shows an average detection accuracy of 97.15, 99.30, and 96.97 for DVMM v1, CASIA v1, and DVMM v2, respectively. These results outperform several current image splicing detection methods. © 2018, The Natural Computing Applications Forum. |
| first_indexed | 2024-03-06T06:01:33Z |
| format | Article |
| id | um.eprints-24017 |
| institution | Universiti Malaya |
| last_indexed | 2024-03-06T06:01:33Z |
| publishDate | 2019 |
| publisher | Springer Verlag (Germany) |
| record_format | dspace |
| spelling | um.eprints-240172020-03-12T02:04:57Z http://eprints.um.edu.my/24017/ Image splicing forgery detection based on low-dimensional singular value decomposition of discrete cosine transform coefficients Moghaddasi, Zahra Jalab, Hamid Abdullah Noor, Rafidah Md QA75 Electronic computers. Computer science Digital image forgery has significantly increased due to the rapid development of several tools of image manipulation. Based on the manipulation used to produce a tampered image, image forgery techniques can be characterized into three types: copy–move forgery, image splicing, and image retouching. Image splicing is achieved by adding regions from one image into another. This technique changes the content of the target image and causes variations in image features which are used to detect the forgery regions. In this study, an image splicing forgery detection method based on low-dimensional singular value decomposition of discrete cosine transform (DCT) coefficients has been presented. The suspicious input image is divided into multi-size blocks, and each block is transformed into 2D DCT. The DCT coefficients are calculated correspondingly to each block. The features from DCT are extracted using SVD algorithm. The roughness measure is calculated for the set of singular values obtained. Lastly, four types of statistical features—mean, variance, third-order moment skewness, and fourth-order moment kurtosis—are extracted from SVD features and are then arranged in a feature vector. Feature reduction has been applied by kernel principal component analysis. Finally, support vector machine is used to distinguish between the authenticated and spliced images. The proposed method was evaluated against three standard image datasets CASIA v1, DVMM v1, and DVMM v2. The proposed method shows an average detection accuracy of 97.15, 99.30, and 96.97 for DVMM v1, CASIA v1, and DVMM v2, respectively. These results outperform several current image splicing detection methods. © 2018, The Natural Computing Applications Forum. Springer Verlag (Germany) 2019 Article PeerReviewed Moghaddasi, Zahra and Jalab, Hamid Abdullah and Noor, Rafidah Md (2019) Image splicing forgery detection based on low-dimensional singular value decomposition of discrete cosine transform coefficients. Neural Computing and Applications, 31 (11). pp. 7867-7877. ISSN 0941-0643, DOI https://doi.org/10.1007/s00521-018-3586-y <https://doi.org/10.1007/s00521-018-3586-y>. https://doi.org/10.1007/s00521-018-3586-y doi:10.1007/s00521-018-3586-y |
| spellingShingle | QA75 Electronic computers. Computer science Moghaddasi, Zahra Jalab, Hamid Abdullah Noor, Rafidah Md Image splicing forgery detection based on low-dimensional singular value decomposition of discrete cosine transform coefficients |
| title | Image splicing forgery detection based on low-dimensional singular value decomposition of discrete cosine transform coefficients |
| title_full | Image splicing forgery detection based on low-dimensional singular value decomposition of discrete cosine transform coefficients |
| title_fullStr | Image splicing forgery detection based on low-dimensional singular value decomposition of discrete cosine transform coefficients |
| title_full_unstemmed | Image splicing forgery detection based on low-dimensional singular value decomposition of discrete cosine transform coefficients |
| title_short | Image splicing forgery detection based on low-dimensional singular value decomposition of discrete cosine transform coefficients |
| title_sort | image splicing forgery detection based on low dimensional singular value decomposition of discrete cosine transform coefficients |
| topic | QA75 Electronic computers. Computer science |
| work_keys_str_mv | AT moghaddasizahra imagesplicingforgerydetectionbasedonlowdimensionalsingularvaluedecompositionofdiscretecosinetransformcoefficients AT jalabhamidabdullah imagesplicingforgerydetectionbasedonlowdimensionalsingularvaluedecompositionofdiscretecosinetransformcoefficients AT noorrafidahmd imagesplicingforgerydetectionbasedonlowdimensionalsingularvaluedecompositionofdiscretecosinetransformcoefficients |