MSRD-CNN: Multi-Scale Residual Deep CNN for General-Purpose Image Manipulation Detection
The authenticity of digital images is a major concern in multimedia forensics due to the availability of advanced photo editing tools/devices. In the literature, several image forensic methods are available to detect specific image processing or editing operations. However, it remains a challenging...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9758710/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536159289704448 |
|---|---|
| author | Kapil Rana Gurinder Singh Puneet Goyal |
| author_facet | Kapil Rana Gurinder Singh Puneet Goyal |
| author_sort | Kapil Rana |
| collection | DOAJ |
| description | The authenticity of digital images is a major concern in multimedia forensics due to the availability of advanced photo editing tools/devices. In the literature, several image forensic methods are available to detect specific image processing or editing operations. However, it remains a challenging task to design a universal forensic method that can detect multiple image editing operations. In this paper, a novel Multi-Scale Residual Deep CNN (MSRD-CNN) is designed to learn the image manipulation features adaptively for multiple image manipulation detection. Our network comprises of three stages: pre-processing, hierarchical high-level feature extraction, and classification. Firstly, a multi-scale residual module is employed in pre-processing stage to extract the prediction error or noise features adaptively. Afterwards, the obtained noise features are processed by feature extraction network having multiple Feature Extraction Blocks (FEBs) for the extraction of high-level image tampering features. Lastly, the resultant feature map is provided to the fully-connected dense layer for classification. The experiment results show that our model surpasses the existing schemes even under anti-forensic attacks, when evaluated on large-scale datasets by considering multiple image processing operations. The proposed network provides overall classification accuracies of 97.07% and 97.48% for BOSSBase and Dresden datasets, respectively. |
| format | Article |
| id | doaj-art-1e8f2dbadd8e4879b97b71c9704cc82f |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-1e8f2dbadd8e4879b97b71c9704cc82f2025-01-15T00:01:02ZengIEEEIEEE Access2169-35362022-01-0110412674127510.1109/ACCESS.2022.31677149758710MSRD-CNN: Multi-Scale Residual Deep CNN for General-Purpose Image Manipulation DetectionKapil Rana0https://orcid.org/0000-0001-8063-8087Gurinder Singh1Puneet Goyal2https://orcid.org/0000-0002-6196-9347Indian Institute of Technology Ropar, Rupnagar, Punjab, IndiaIndian Institute of Technology Ropar, Rupnagar, Punjab, IndiaIndian Institute of Technology Ropar, Rupnagar, Punjab, IndiaThe authenticity of digital images is a major concern in multimedia forensics due to the availability of advanced photo editing tools/devices. In the literature, several image forensic methods are available to detect specific image processing or editing operations. However, it remains a challenging task to design a universal forensic method that can detect multiple image editing operations. In this paper, a novel Multi-Scale Residual Deep CNN (MSRD-CNN) is designed to learn the image manipulation features adaptively for multiple image manipulation detection. Our network comprises of three stages: pre-processing, hierarchical high-level feature extraction, and classification. Firstly, a multi-scale residual module is employed in pre-processing stage to extract the prediction error or noise features adaptively. Afterwards, the obtained noise features are processed by feature extraction network having multiple Feature Extraction Blocks (FEBs) for the extraction of high-level image tampering features. Lastly, the resultant feature map is provided to the fully-connected dense layer for classification. The experiment results show that our model surpasses the existing schemes even under anti-forensic attacks, when evaluated on large-scale datasets by considering multiple image processing operations. The proposed network provides overall classification accuracies of 97.07% and 97.48% for BOSSBase and Dresden datasets, respectively.https://ieeexplore.ieee.org/document/9758710/Multiple image manipulation detectionanti-forensic attacksconvolutional neural networksmulti-scale residual module |
| spellingShingle | Kapil Rana Gurinder Singh Puneet Goyal MSRD-CNN: Multi-Scale Residual Deep CNN for General-Purpose Image Manipulation Detection IEEE Access Multiple image manipulation detection anti-forensic attacks convolutional neural networks multi-scale residual module |
| title | MSRD-CNN: Multi-Scale Residual Deep CNN for General-Purpose Image Manipulation Detection |
| title_full | MSRD-CNN: Multi-Scale Residual Deep CNN for General-Purpose Image Manipulation Detection |
| title_fullStr | MSRD-CNN: Multi-Scale Residual Deep CNN for General-Purpose Image Manipulation Detection |
| title_full_unstemmed | MSRD-CNN: Multi-Scale Residual Deep CNN for General-Purpose Image Manipulation Detection |
| title_short | MSRD-CNN: Multi-Scale Residual Deep CNN for General-Purpose Image Manipulation Detection |
| title_sort | msrd cnn multi scale residual deep cnn for general purpose image manipulation detection |
| topic | Multiple image manipulation detection anti-forensic attacks convolutional neural networks multi-scale residual module |
| url | https://ieeexplore.ieee.org/document/9758710/ |
| work_keys_str_mv | AT kapilrana msrdcnnmultiscaleresidualdeepcnnforgeneralpurposeimagemanipulationdetection AT gurindersingh msrdcnnmultiscaleresidualdeepcnnforgeneralpurposeimagemanipulationdetection AT puneetgoyal msrdcnnmultiscaleresidualdeepcnnforgeneralpurposeimagemanipulationdetection |