Inpainting forgery detection using hybrid generative/discriminative approach based on bounded generalized Gaussian mixture model
We propose in this paper a novel reliable detection method to recognize forged inpainting images. Detecting potential forgeries and authenticating the content of digital images is extremely challenging and important for many applications. The proposed approach involves developing new probabilistic s...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Emerald Publishing
2024-01-01
|
| Series: | Applied Computing and Informatics |
| Subjects: | |
| Online Access: | https://www.emerald.com/insight/content/doi/10.1016/j.aci.2019.12.001/full/pdf |
| _version_ | 1797367173158535168 |
|---|---|
| author | Abdullah Alharbi Wajdi Alhakami Sami Bourouis Fatma Najar Nizar Bouguila |
| author_facet | Abdullah Alharbi Wajdi Alhakami Sami Bourouis Fatma Najar Nizar Bouguila |
| author_sort | Abdullah Alharbi |
| collection | DOAJ |
| description | We propose in this paper a novel reliable detection method to recognize forged inpainting images. Detecting potential forgeries and authenticating the content of digital images is extremely challenging and important for many applications. The proposed approach involves developing new probabilistic support vector machines (SVMs) kernels from a flexible generative statistical model named “bounded generalized Gaussian mixture model”. The developed learning framework has the advantage to combine properly the benefits of both discriminative and generative models and to include prior knowledge about the nature of data. It can effectively recognize if an image is a tampered one and also to identify both forged and authentic images. The obtained results confirmed that the developed framework has good performance under numerous inpainted images. |
| first_indexed | 2024-03-08T17:14:31Z |
| format | Article |
| id | doaj.art-12a48ddba95943b99e29a0ba6bcbec9f |
| institution | Directory Open Access Journal |
| issn | 2634-1964 2210-8327 |
| language | English |
| last_indexed | 2024-03-08T17:14:31Z |
| publishDate | 2024-01-01 |
| publisher | Emerald Publishing |
| record_format | Article |
| series | Applied Computing and Informatics |
| spelling | doaj.art-12a48ddba95943b99e29a0ba6bcbec9f2024-01-03T15:21:48ZengEmerald PublishingApplied Computing and Informatics2634-19642210-83272024-01-01201/28910410.1016/j.aci.2019.12.001Inpainting forgery detection using hybrid generative/discriminative approach based on bounded generalized Gaussian mixture modelAbdullah Alharbi0Wajdi Alhakami1Sami Bourouis2Fatma Najar3Nizar Bouguila4College of Computers and Information Technology, Taif University, Taif, Saudi ArabiaCollege of Computers and Information Technology, Taif University, Taif, Saudi ArabiaCollege of Computers and Information Technology, Taif University, Taif, Saudi ArabiaUniversité de Tunis El Manar, LR-SITI Laboratoire Signal, Image et Technologies de l'Information, Tunis, TunisiaThe Concordia Institute for Information Systems Engineering (CIISE), Concordia University, Montreal, CanadaWe propose in this paper a novel reliable detection method to recognize forged inpainting images. Detecting potential forgeries and authenticating the content of digital images is extremely challenging and important for many applications. The proposed approach involves developing new probabilistic support vector machines (SVMs) kernels from a flexible generative statistical model named “bounded generalized Gaussian mixture model”. The developed learning framework has the advantage to combine properly the benefits of both discriminative and generative models and to include prior knowledge about the nature of data. It can effectively recognize if an image is a tampered one and also to identify both forged and authentic images. The obtained results confirmed that the developed framework has good performance under numerous inpainted images.https://www.emerald.com/insight/content/doi/10.1016/j.aci.2019.12.001/full/pdfForgery detectionMixture modelsBounded generalized Gaussian mixture modelSVM kernelsStatistical machine learningBig data |
| spellingShingle | Abdullah Alharbi Wajdi Alhakami Sami Bourouis Fatma Najar Nizar Bouguila Inpainting forgery detection using hybrid generative/discriminative approach based on bounded generalized Gaussian mixture model Applied Computing and Informatics Forgery detection Mixture models Bounded generalized Gaussian mixture model SVM kernels Statistical machine learning Big data |
| title | Inpainting forgery detection using hybrid generative/discriminative approach based on bounded generalized Gaussian mixture model |
| title_full | Inpainting forgery detection using hybrid generative/discriminative approach based on bounded generalized Gaussian mixture model |
| title_fullStr | Inpainting forgery detection using hybrid generative/discriminative approach based on bounded generalized Gaussian mixture model |
| title_full_unstemmed | Inpainting forgery detection using hybrid generative/discriminative approach based on bounded generalized Gaussian mixture model |
| title_short | Inpainting forgery detection using hybrid generative/discriminative approach based on bounded generalized Gaussian mixture model |
| title_sort | inpainting forgery detection using hybrid generative discriminative approach based on bounded generalized gaussian mixture model |
| topic | Forgery detection Mixture models Bounded generalized Gaussian mixture model SVM kernels Statistical machine learning Big data |
| url | https://www.emerald.com/insight/content/doi/10.1016/j.aci.2019.12.001/full/pdf |
| work_keys_str_mv | AT abdullahalharbi inpaintingforgerydetectionusinghybridgenerativediscriminativeapproachbasedonboundedgeneralizedgaussianmixturemodel AT wajdialhakami inpaintingforgerydetectionusinghybridgenerativediscriminativeapproachbasedonboundedgeneralizedgaussianmixturemodel AT samibourouis inpaintingforgerydetectionusinghybridgenerativediscriminativeapproachbasedonboundedgeneralizedgaussianmixturemodel AT fatmanajar inpaintingforgerydetectionusinghybridgenerativediscriminativeapproachbasedonboundedgeneralizedgaussianmixturemodel AT nizarbouguila inpaintingforgerydetectionusinghybridgenerativediscriminativeapproachbasedonboundedgeneralizedgaussianmixturemodel |