Pri-EMO: A universal perturbation method for privacy preserving facial emotion recognition
Facial emotion have great significance in human-computer interaction, virtual reality and people's communication. Existing methods for facial emotion privacy mainly concentrate on the perturbation of facial emotion images. However, cryptography-based perturbation algorithms are highly computati...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2023-11-01
|
| Series: | Journal of Information and Intelligence |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2949715923000513 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839642914390540288 |
|---|---|
| author | Yong Zeng Zhenyu Zhang Jiale Liu Jianfeng Ma Zhihong Liu |
| author_facet | Yong Zeng Zhenyu Zhang Jiale Liu Jianfeng Ma Zhihong Liu |
| author_sort | Yong Zeng |
| collection | DOAJ |
| description | Facial emotion have great significance in human-computer interaction, virtual reality and people's communication. Existing methods for facial emotion privacy mainly concentrate on the perturbation of facial emotion images. However, cryptography-based perturbation algorithms are highly computationally expensive, and transformation-based perturbation algorithms only target specific recognition models. In this paper, we propose a universal feature vector-based privacy-preserving perturbation algorithm for facial emotion. Our method implements privacy-preserving facial emotion images on the feature space by computing tiny perturbations and adding them to the original images. In addition, the proposed algorithm can also enable expression images to be recognized as specific labels. Experiments show that the protection success rate of our method is above 95% and the image quality evaluation degrades no more than 0.003. The quantitative and qualitative results show that our proposed method has a balance between privacy and usability. |
| format | Article |
| id | doaj-art-2f3ef3d45f1a47f3a9ee5f68641c1cef |
| institution | Matheson Library |
| issn | 2949-7159 |
| language | English |
| publishDate | 2023-11-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Journal of Information and Intelligence |
| spelling | doaj-art-2f3ef3d45f1a47f3a9ee5f68641c1cef2025-07-02T05:22:40ZengKeAi Communications Co., Ltd.Journal of Information and Intelligence2949-71592023-11-0114330340Pri-EMO: A universal perturbation method for privacy preserving facial emotion recognitionYong Zeng0Zhenyu Zhang1Jiale Liu2Jianfeng Ma3Zhihong Liu4Corresponding author.; School of Cyber Engineering, Xidian University, Xi'an 710071, ChinaSchool of Cyber Engineering, Xidian University, Xi'an 710071, ChinaSchool of Cyber Engineering, Xidian University, Xi'an 710071, ChinaSchool of Cyber Engineering, Xidian University, Xi'an 710071, ChinaSchool of Cyber Engineering, Xidian University, Xi'an 710071, ChinaFacial emotion have great significance in human-computer interaction, virtual reality and people's communication. Existing methods for facial emotion privacy mainly concentrate on the perturbation of facial emotion images. However, cryptography-based perturbation algorithms are highly computationally expensive, and transformation-based perturbation algorithms only target specific recognition models. In this paper, we propose a universal feature vector-based privacy-preserving perturbation algorithm for facial emotion. Our method implements privacy-preserving facial emotion images on the feature space by computing tiny perturbations and adding them to the original images. In addition, the proposed algorithm can also enable expression images to be recognized as specific labels. Experiments show that the protection success rate of our method is above 95% and the image quality evaluation degrades no more than 0.003. The quantitative and qualitative results show that our proposed method has a balance between privacy and usability.http://www.sciencedirect.com/science/article/pii/S2949715923000513Facial emotion recognitionPrivacy preservingPerturbationUniversal algorithmFeature space |
| spellingShingle | Yong Zeng Zhenyu Zhang Jiale Liu Jianfeng Ma Zhihong Liu Pri-EMO: A universal perturbation method for privacy preserving facial emotion recognition Journal of Information and Intelligence Facial emotion recognition Privacy preserving Perturbation Universal algorithm Feature space |
| title | Pri-EMO: A universal perturbation method for privacy preserving facial emotion recognition |
| title_full | Pri-EMO: A universal perturbation method for privacy preserving facial emotion recognition |
| title_fullStr | Pri-EMO: A universal perturbation method for privacy preserving facial emotion recognition |
| title_full_unstemmed | Pri-EMO: A universal perturbation method for privacy preserving facial emotion recognition |
| title_short | Pri-EMO: A universal perturbation method for privacy preserving facial emotion recognition |
| title_sort | pri emo a universal perturbation method for privacy preserving facial emotion recognition |
| topic | Facial emotion recognition Privacy preserving Perturbation Universal algorithm Feature space |
| url | http://www.sciencedirect.com/science/article/pii/S2949715923000513 |
| work_keys_str_mv | AT yongzeng priemoauniversalperturbationmethodforprivacypreservingfacialemotionrecognition AT zhenyuzhang priemoauniversalperturbationmethodforprivacypreservingfacialemotionrecognition AT jialeliu priemoauniversalperturbationmethodforprivacypreservingfacialemotionrecognition AT jianfengma priemoauniversalperturbationmethodforprivacypreservingfacialemotionrecognition AT zhihongliu priemoauniversalperturbationmethodforprivacypreservingfacialemotionrecognition |