Effects of image compression on face image manipulation detection: A case study on facial retouching
Abstract Numerous methods have been introduced to reliably detect digital face image manipulations in the past. Of late, the generalisability of these schemes has been questioned in particular with respect to image post‐processing. Image compression represents a post‐processing which is frequently a...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-05-01
|
| Series: | IET Biometrics |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/bme2.12027 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832546716841148416 |
|---|---|
| author | Christian Rathgeb Kevin Bernardo Nathania E. Haryanto Christoph Busch |
| author_facet | Christian Rathgeb Kevin Bernardo Nathania E. Haryanto Christoph Busch |
| author_sort | Christian Rathgeb |
| collection | DOAJ |
| description | Abstract Numerous methods have been introduced to reliably detect digital face image manipulations in the past. Of late, the generalisability of these schemes has been questioned in particular with respect to image post‐processing. Image compression represents a post‐processing which is frequently applied in diverse biometric application scenarios. Severe compression might erase digital traces of face image manipulation and hence hamper a reliable detection thereof. In this work, the effects of image compression on the face image manipulation detection are analysed. In particular, a case study on facial retouching detection under the influence of image compression is presented. To this end, ICAO‐compliant subsets of two public face databases are used to automatically create a database containing more than 9000 retouched reference images together with unconstrained probe images. Subsequently, reference images are compressed applying JPEG and JPEG 2000 at compression levels recommended for face image storage in electronic travel documents. Novel detection algorithms utilising texture descriptors and deep face representations are proposed and evaluated in a single image and differential scenario. Results obtained from challenging cross‐database experiments in which the analysed retouching technique is unknown during training yield interesting findings: (1) most competitive detection performance is achieved for differential scenarios employing deep face representations; (2) image compression severely impacts the performance of face image manipulation detection schemes based on texture descriptors while methods utilising deep face representations are found to be highly robust; (3) in some cases, the application of image compression might as well improve detection performance. |
| format | Article |
| id | doaj-art-1c5b467e60124d5d87916840ccb34a89 |
| institution | Kabale University |
| issn | 2047-4938 2047-4946 |
| language | English |
| publishDate | 2021-05-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Biometrics |
| spelling | doaj-art-1c5b467e60124d5d87916840ccb34a892025-02-03T06:47:27ZengWileyIET Biometrics2047-49382047-49462021-05-0110334235510.1049/bme2.12027Effects of image compression on face image manipulation detection: A case study on facial retouchingChristian Rathgeb0Kevin Bernardo1Nathania E. Haryanto2Christoph Busch3da/sec—Biometrics and Internet Security Research Group Hochschule Darmstadt Darmstadt Germanyda/sec—Biometrics and Internet Security Research Group Hochschule Darmstadt Darmstadt Germanyda/sec—Biometrics and Internet Security Research Group Hochschule Darmstadt Darmstadt Germanyda/sec—Biometrics and Internet Security Research Group Hochschule Darmstadt Darmstadt GermanyAbstract Numerous methods have been introduced to reliably detect digital face image manipulations in the past. Of late, the generalisability of these schemes has been questioned in particular with respect to image post‐processing. Image compression represents a post‐processing which is frequently applied in diverse biometric application scenarios. Severe compression might erase digital traces of face image manipulation and hence hamper a reliable detection thereof. In this work, the effects of image compression on the face image manipulation detection are analysed. In particular, a case study on facial retouching detection under the influence of image compression is presented. To this end, ICAO‐compliant subsets of two public face databases are used to automatically create a database containing more than 9000 retouched reference images together with unconstrained probe images. Subsequently, reference images are compressed applying JPEG and JPEG 2000 at compression levels recommended for face image storage in electronic travel documents. Novel detection algorithms utilising texture descriptors and deep face representations are proposed and evaluated in a single image and differential scenario. Results obtained from challenging cross‐database experiments in which the analysed retouching technique is unknown during training yield interesting findings: (1) most competitive detection performance is achieved for differential scenarios employing deep face representations; (2) image compression severely impacts the performance of face image manipulation detection schemes based on texture descriptors while methods utilising deep face representations are found to be highly robust; (3) in some cases, the application of image compression might as well improve detection performance.https://doi.org/10.1049/bme2.12027biometrics (access control)data compressionface recognitionfeature extractionimage codingimage texture |
| spellingShingle | Christian Rathgeb Kevin Bernardo Nathania E. Haryanto Christoph Busch Effects of image compression on face image manipulation detection: A case study on facial retouching IET Biometrics biometrics (access control) data compression face recognition feature extraction image coding image texture |
| title | Effects of image compression on face image manipulation detection: A case study on facial retouching |
| title_full | Effects of image compression on face image manipulation detection: A case study on facial retouching |
| title_fullStr | Effects of image compression on face image manipulation detection: A case study on facial retouching |
| title_full_unstemmed | Effects of image compression on face image manipulation detection: A case study on facial retouching |
| title_short | Effects of image compression on face image manipulation detection: A case study on facial retouching |
| title_sort | effects of image compression on face image manipulation detection a case study on facial retouching |
| topic | biometrics (access control) data compression face recognition feature extraction image coding image texture |
| url | https://doi.org/10.1049/bme2.12027 |
| work_keys_str_mv | AT christianrathgeb effectsofimagecompressiononfaceimagemanipulationdetectionacasestudyonfacialretouching AT kevinbernardo effectsofimagecompressiononfaceimagemanipulationdetectionacasestudyonfacialretouching AT nathaniaeharyanto effectsofimagecompressiononfaceimagemanipulationdetectionacasestudyonfacialretouching AT christophbusch effectsofimagecompressiononfaceimagemanipulationdetectionacasestudyonfacialretouching |