A Detection Approach Using LSTM-CNN for Object Removal Caused by Exemplar-Based Image Inpainting
Exemplar-based image inpainting technology is a “double-edged sword”. It can not only restore the integrity of image by inpainting damaged or removed regions, but can also tamper with the image by using the pixels around the object region to fill in the gaps left by object removal. Through the resea...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-05-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/9/5/858 |
| _version_ | 1797567241282125824 |
|---|---|
| author | Ming Lu Shaozhang Niu |
| author_facet | Ming Lu Shaozhang Niu |
| author_sort | Ming Lu |
| collection | DOAJ |
| description | Exemplar-based image inpainting technology is a “double-edged sword”. It can not only restore the integrity of image by inpainting damaged or removed regions, but can also tamper with the image by using the pixels around the object region to fill in the gaps left by object removal. Through the research and analysis, it is found that the existing exemplar-based image inpainting forensics methods generally have the following disadvantages: the abnormal similar patches are time-consuming and inaccurate to search, have a high false alarm rate and a lack of robustness to multiple post-processing combined operations. In view of the above shortcomings, a detection method based on long short-term memory (LSTM)-convolutional neural network (CNN) for image object removal is proposed. In this method, CNN is used to search for abnormal similar patches. Because of CNN’s strong learning ability, it improves the speed and accuracy of the search. The LSTM network is used to eliminate the influence of false alarm patches on detection results and reduce the false alarm rate. A filtering module is designed to eliminate the attack of post-processing operation. Experimental results show that the method has a high accuracy, and can resist the attack of post-processing combination operations. It can achieve a better performance than the state-of-the-art approaches. |
| first_indexed | 2024-03-10T19:38:53Z |
| format | Article |
| id | doaj.art-aa173bea3b2048a887ee8df5413040ce |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T19:38:53Z |
| publishDate | 2020-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-aa173bea3b2048a887ee8df5413040ce2023-11-20T01:25:04ZengMDPI AGElectronics2079-92922020-05-019585810.3390/electronics9050858A Detection Approach Using LSTM-CNN for Object Removal Caused by Exemplar-Based Image InpaintingMing Lu0Shaozhang Niu1Beijing Key Lab of Intelligent Telecommunication Software and Multimedia, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaBeijing Key Lab of Intelligent Telecommunication Software and Multimedia, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaExemplar-based image inpainting technology is a “double-edged sword”. It can not only restore the integrity of image by inpainting damaged or removed regions, but can also tamper with the image by using the pixels around the object region to fill in the gaps left by object removal. Through the research and analysis, it is found that the existing exemplar-based image inpainting forensics methods generally have the following disadvantages: the abnormal similar patches are time-consuming and inaccurate to search, have a high false alarm rate and a lack of robustness to multiple post-processing combined operations. In view of the above shortcomings, a detection method based on long short-term memory (LSTM)-convolutional neural network (CNN) for image object removal is proposed. In this method, CNN is used to search for abnormal similar patches. Because of CNN’s strong learning ability, it improves the speed and accuracy of the search. The LSTM network is used to eliminate the influence of false alarm patches on detection results and reduce the false alarm rate. A filtering module is designed to eliminate the attack of post-processing operation. Experimental results show that the method has a high accuracy, and can resist the attack of post-processing combination operations. It can achieve a better performance than the state-of-the-art approaches.https://www.mdpi.com/2079-9292/9/5/858digital image forensicsobject removalimage inpaintingconvolutional neural networklong short-term memory networkdeep learning |
| spellingShingle | Ming Lu Shaozhang Niu A Detection Approach Using LSTM-CNN for Object Removal Caused by Exemplar-Based Image Inpainting Electronics digital image forensics object removal image inpainting convolutional neural network long short-term memory network deep learning |
| title | A Detection Approach Using LSTM-CNN for Object Removal Caused by Exemplar-Based Image Inpainting |
| title_full | A Detection Approach Using LSTM-CNN for Object Removal Caused by Exemplar-Based Image Inpainting |
| title_fullStr | A Detection Approach Using LSTM-CNN for Object Removal Caused by Exemplar-Based Image Inpainting |
| title_full_unstemmed | A Detection Approach Using LSTM-CNN for Object Removal Caused by Exemplar-Based Image Inpainting |
| title_short | A Detection Approach Using LSTM-CNN for Object Removal Caused by Exemplar-Based Image Inpainting |
| title_sort | detection approach using lstm cnn for object removal caused by exemplar based image inpainting |
| topic | digital image forensics object removal image inpainting convolutional neural network long short-term memory network deep learning |
| url | https://www.mdpi.com/2079-9292/9/5/858 |
| work_keys_str_mv | AT minglu adetectionapproachusinglstmcnnforobjectremovalcausedbyexemplarbasedimageinpainting AT shaozhangniu adetectionapproachusinglstmcnnforobjectremovalcausedbyexemplarbasedimageinpainting AT minglu detectionapproachusinglstmcnnforobjectremovalcausedbyexemplarbasedimageinpainting AT shaozhangniu detectionapproachusinglstmcnnforobjectremovalcausedbyexemplarbasedimageinpainting |