A two-stage detection method of copy-move forgery based on parallel feature fusion
Abstract The copy-move forgery refers to the copying and pasting of a region of the original image into the target region of the same image, which represents a typical tampering method with the characteristics of easy tampering and high-quality tampering. The existing single feature-based methods of...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2022-04-01
|
| Series: | EURASIP Journal on Wireless Communications and Networking |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13638-022-02112-8 |
| _version_ | 1819052440668864512 |
|---|---|
| author | Wujian Ye Qingyuan Zeng Yihang Peng Yijun Liu Chin-Chen Chang |
| author_facet | Wujian Ye Qingyuan Zeng Yihang Peng Yijun Liu Chin-Chen Chang |
| author_sort | Wujian Ye |
| collection | DOAJ |
| description | Abstract The copy-move forgery refers to the copying and pasting of a region of the original image into the target region of the same image, which represents a typical tampering method with the characteristics of easy tampering and high-quality tampering. The existing single feature-based methods of forgery detection have certain shortcomings, such as high false alarm rate, low robustness, and low detection accuracy. To address these shortcomings, this paper proposes an improved two-stage detection method based on parallel feature fusion and an adaptive threshold generation algorithm. Firstly, the SLIC super-pixels segmentation algorithm is used for image preprocessing, and a similar region extraction algorithm without threshold is employed to obtain the suspected tampering regions with high similarity. Secondly, the parallel fusion feature is obtained based on the SIFT and HU features to express the characteristics of local regions. Then, the corresponding threshold value is generated based on the histogram of oriented gradient (HOG) to describe the texture characteristics of the obtained regions, which acts as a criterion to judge whether a region has been forged or not. The experimental results show that the proposed method outperforms the existing methods, achieving the accuracy of 99.01% and 98.5% on the MICC-F220 and MICC-F2000 datasets respectively. In addition, the proposed method has stronger robustness performance on COMOFOD dataset than the comparison methods. |
| first_indexed | 2024-12-21T12:19:52Z |
| format | Article |
| id | doaj.art-e71f7df87b77424bafba845e2933c8b2 |
| institution | Directory Open Access Journal |
| issn | 1687-1499 |
| language | English |
| last_indexed | 2024-12-21T12:19:52Z |
| publishDate | 2022-04-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Wireless Communications and Networking |
| spelling | doaj.art-e71f7df87b77424bafba845e2933c8b22022-12-21T19:04:21ZengSpringerOpenEURASIP Journal on Wireless Communications and Networking1687-14992022-04-012022112210.1186/s13638-022-02112-8A two-stage detection method of copy-move forgery based on parallel feature fusionWujian Ye0Qingyuan Zeng1Yihang Peng2Yijun Liu3Chin-Chen Chang4School of Information Engineering, Guangdong University of TechnologySchool of Information Engineering, Guangdong University of TechnologySchool of Information Engineering, Guangdong University of TechnologySchool of Information Engineering, Guangdong University of TechnologyDepartment of Information Engineering and Computer Science, Feng Chia UniversityAbstract The copy-move forgery refers to the copying and pasting of a region of the original image into the target region of the same image, which represents a typical tampering method with the characteristics of easy tampering and high-quality tampering. The existing single feature-based methods of forgery detection have certain shortcomings, such as high false alarm rate, low robustness, and low detection accuracy. To address these shortcomings, this paper proposes an improved two-stage detection method based on parallel feature fusion and an adaptive threshold generation algorithm. Firstly, the SLIC super-pixels segmentation algorithm is used for image preprocessing, and a similar region extraction algorithm without threshold is employed to obtain the suspected tampering regions with high similarity. Secondly, the parallel fusion feature is obtained based on the SIFT and HU features to express the characteristics of local regions. Then, the corresponding threshold value is generated based on the histogram of oriented gradient (HOG) to describe the texture characteristics of the obtained regions, which acts as a criterion to judge whether a region has been forged or not. The experimental results show that the proposed method outperforms the existing methods, achieving the accuracy of 99.01% and 98.5% on the MICC-F220 and MICC-F2000 datasets respectively. In addition, the proposed method has stronger robustness performance on COMOFOD dataset than the comparison methods.https://doi.org/10.1186/s13638-022-02112-8Copy-move forgeryTwo-stage forgery detectionSuper-pixel segmentationParallel feature fusionAdaptive threshold |
| spellingShingle | Wujian Ye Qingyuan Zeng Yihang Peng Yijun Liu Chin-Chen Chang A two-stage detection method of copy-move forgery based on parallel feature fusion EURASIP Journal on Wireless Communications and Networking Copy-move forgery Two-stage forgery detection Super-pixel segmentation Parallel feature fusion Adaptive threshold |
| title | A two-stage detection method of copy-move forgery based on parallel feature fusion |
| title_full | A two-stage detection method of copy-move forgery based on parallel feature fusion |
| title_fullStr | A two-stage detection method of copy-move forgery based on parallel feature fusion |
| title_full_unstemmed | A two-stage detection method of copy-move forgery based on parallel feature fusion |
| title_short | A two-stage detection method of copy-move forgery based on parallel feature fusion |
| title_sort | two stage detection method of copy move forgery based on parallel feature fusion |
| topic | Copy-move forgery Two-stage forgery detection Super-pixel segmentation Parallel feature fusion Adaptive threshold |
| url | https://doi.org/10.1186/s13638-022-02112-8 |
| work_keys_str_mv | AT wujianye atwostagedetectionmethodofcopymoveforgerybasedonparallelfeaturefusion AT qingyuanzeng atwostagedetectionmethodofcopymoveforgerybasedonparallelfeaturefusion AT yihangpeng atwostagedetectionmethodofcopymoveforgerybasedonparallelfeaturefusion AT yijunliu atwostagedetectionmethodofcopymoveforgerybasedonparallelfeaturefusion AT chinchenchang atwostagedetectionmethodofcopymoveforgerybasedonparallelfeaturefusion AT wujianye twostagedetectionmethodofcopymoveforgerybasedonparallelfeaturefusion AT qingyuanzeng twostagedetectionmethodofcopymoveforgerybasedonparallelfeaturefusion AT yihangpeng twostagedetectionmethodofcopymoveforgerybasedonparallelfeaturefusion AT yijunliu twostagedetectionmethodofcopymoveforgerybasedonparallelfeaturefusion AT chinchenchang twostagedetectionmethodofcopymoveforgerybasedonparallelfeaturefusion |