CMF-iteMS: An automatic threshold selection for detection of copy-move forgery
Taking into consideration that the prior CMF detection methods rely on several fixed threshold values in the filtering process, we propose an efficient CMF detection method with an automatic threshold selection, named as CMF-iteMS. The CMF-iteMS recommends a PatchMatch-based CMF detection method tha...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Published: |
Elsevier
2019
|
| Subjects: | |
| Online Access: | http://eprints.um.edu.my/20149/ https://doi.org/10.1016/j.forsciint.2018.12.004 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1831506743465607168 |
|---|---|
| author | Abd Warif, Nor Bakiah Idris, Mohd Yamani Idna Wahab, Ainuddin Wahid Abdul Salleh, Rosli Ismail, Ahsiah |
| author_facet | Abd Warif, Nor Bakiah Idris, Mohd Yamani Idna Wahab, Ainuddin Wahid Abdul Salleh, Rosli Ismail, Ahsiah |
| author_sort | Abd Warif, Nor Bakiah |
| building | UM Library |
| collection | Institutional Repository |
| content_provider | Universiti Malaya |
| content_source | UM Research Repository |
| continent | Asia |
| country | Malaysia |
| description | Taking into consideration that the prior CMF detection methods rely on several fixed threshold values in the filtering process, we propose an efficient CMF detection method with an automatic threshold selection, named as CMF-iteMS. The CMF-iteMS recommends a PatchMatch-based CMF detection method that adapts Fourier-Mellin Transform (FMT) as the feature extraction technique while a new automatic threshold selection based on iterative means of regions size (iteMS) procedure is introduced to have flexibility in changing the threshold value for various characteristics (quality, sizes, and attacks) in each input image. To ensure the reliability of the proposed CMF-iteMS, the method is compared with four state-of-the-art CMF detection methods based on Scale Invariant Feature Transform (SIFT), patch matching, multi-scale analysis and symmetry techniques using three available datasets that cover the variety of characteristics in CMF images. The results show that the F-score of the CMF-iteMS outperformed existing CMF detection methods by exceeding an average of 90% F-score values for image-level evaluation and 82% of F-score value for pixel-level evaluation for all datasets in original size. As special attention is given to the image resizing attack, the method is able to maintain the highest performance even if the images in the datasets are resized to 0.25 parameter. |
| format | Article |
| id | my.um.eprints-20149 |
| institution | Universiti Malaya |
| publishDate | 2019 |
| publisher | Elsevier |
| record_format | eprints |
| spelling | my.um.eprints-201492019-01-23T09:05:15Z http://eprints.um.edu.my/20149/ CMF-iteMS: An automatic threshold selection for detection of copy-move forgery Abd Warif, Nor Bakiah Idris, Mohd Yamani Idna Wahab, Ainuddin Wahid Abdul Salleh, Rosli Ismail, Ahsiah QA75 Electronic computers. Computer science Taking into consideration that the prior CMF detection methods rely on several fixed threshold values in the filtering process, we propose an efficient CMF detection method with an automatic threshold selection, named as CMF-iteMS. The CMF-iteMS recommends a PatchMatch-based CMF detection method that adapts Fourier-Mellin Transform (FMT) as the feature extraction technique while a new automatic threshold selection based on iterative means of regions size (iteMS) procedure is introduced to have flexibility in changing the threshold value for various characteristics (quality, sizes, and attacks) in each input image. To ensure the reliability of the proposed CMF-iteMS, the method is compared with four state-of-the-art CMF detection methods based on Scale Invariant Feature Transform (SIFT), patch matching, multi-scale analysis and symmetry techniques using three available datasets that cover the variety of characteristics in CMF images. The results show that the F-score of the CMF-iteMS outperformed existing CMF detection methods by exceeding an average of 90% F-score values for image-level evaluation and 82% of F-score value for pixel-level evaluation for all datasets in original size. As special attention is given to the image resizing attack, the method is able to maintain the highest performance even if the images in the datasets are resized to 0.25 parameter. Elsevier 2019 Article PeerReviewed Abd Warif, Nor Bakiah and Idris, Mohd Yamani Idna and Wahab, Ainuddin Wahid Abdul and Salleh, Rosli and Ismail, Ahsiah (2019) CMF-iteMS: An automatic threshold selection for detection of copy-move forgery. Forensic Science International, 295. pp. 83-99. ISSN 0379-0738, DOI https://doi.org/10.1016/j.forsciint.2018.12.004 <https://doi.org/10.1016/j.forsciint.2018.12.004>. https://doi.org/10.1016/j.forsciint.2018.12.004 doi:10.1016/j.forsciint.2018.12.004 |
| spellingShingle | QA75 Electronic computers. Computer science Abd Warif, Nor Bakiah Idris, Mohd Yamani Idna Wahab, Ainuddin Wahid Abdul Salleh, Rosli Ismail, Ahsiah CMF-iteMS: An automatic threshold selection for detection of copy-move forgery |
| title | CMF-iteMS: An automatic threshold selection for detection of copy-move forgery |
| title_full | CMF-iteMS: An automatic threshold selection for detection of copy-move forgery |
| title_fullStr | CMF-iteMS: An automatic threshold selection for detection of copy-move forgery |
| title_full_unstemmed | CMF-iteMS: An automatic threshold selection for detection of copy-move forgery |
| title_short | CMF-iteMS: An automatic threshold selection for detection of copy-move forgery |
| title_sort | cmf-items: an automatic threshold selection for detection of copy-move forgery |
| topic | QA75 Electronic computers. Computer science |
| url | http://eprints.um.edu.my/20149/ https://doi.org/10.1016/j.forsciint.2018.12.004 |
| url_provider | http://eprints.um.edu.my/ |