Convolutional-based variational autoencoders for face privacy protection in video surveillance

Sivalakshmi, Mallepogu; Prasad, K. Rajendra; Bindu, C. Shoba

doi:10.47974/JDMSC-1975

Open Access Research Article

Convolutional-based variational autoencoders for face privacy protection in video surveillance

^*Mallepogu SivalakshmiCorresponding authorshivacse06@gmail.comDepartment of Computer Science and Engineering JNTUA College of EngineeringAnanthapuramu, Andhra Pradesh, IndiaView full profile → , K. Rajendra Prasadkrprgm@gmail.comDepartment of Computer Science and Engineering Institute of Aeronautical EngineeringDepartment of Computer Science and Engineering (Data Science) Institute of Aeronautical Engineering DundigalHyderabad, Telangana, 500043, IndiaView full profile → , C. Shoba Bindushobabindhu.cse@jntua.ac.inDepartment of Computer Science and Engineering JNTUA College of EngineeringAnanthapuramu, Andhra Pradesh, IndiaView full profile →

* Corresponding author · click or hover a name for details

pp. 1205–1214Vol. 27Issue 4June 2024DOI: 10.47974/JDMSC-1975 Crossmark XML

Published Online:: 26 Jun 2024
Article type:: Research Article
Language:: EN
Article no.:: JDMSC-1975
Pages:: 1205–1214

Abstract

The ubiquity of high-quality video surveillance owes much to advancements in imaging technology and data transmission. Presently, exposing an individual’s face in photographs can infringe upon their right to privacy. Real-world face de-identification is a typical task beyond removing private information, considering the specific intent behind image usage. This paper introduces a novel deep learning model (NDLM) designed to safeguard facial privacy in video surveillance, structured around two key phases: face detection and privacy protection. Initially, surveillance video data is collected from online sources. In the initial phase, face detection is achieved through the integration of a Hybrid Convolutional Neural Network (HCNN), which combines a convolutional neural network (CNN) and the improved Fire Hawks algorithm (IFHA) for optimal performance. IFHA assists in ensuring privacy protection. This integration incorporates service quality preservation into the loss function, facilitating the generation of facial images with controlled quality preservation. The approach effectively manages various service quality measures and is adaptable across diverse service contexts. The proposed methodology’s effectiveness is evaluated to demonstrate its efficiency when compared to traditional methods.

Keywords

Face identification Privacy protection Video surveillance Convolutional neural network Fire hawk’s algorithm Quality maintenance-variational autoencoders

Subject Classifications

94A60

References

[1] Li, Mianjie, Zhihong Tian, Xiaojiang Du, Xiaochen Yuan, Chun Shan, and Mohsen Guizani. “Power normalized cepstral robust features of deep neural networks in a cloud computing data privacy protection scheme.” Neurocomputing 518 : 165-173 (2023).
[2] Khosravy, Mahdi, Kazuaki Nakamura, Yuki Hirose, Naoko Nitta, and Noboru Babaguchi. “Model inversion attack by integration of deep generative models: Privacy-sensitive face generation from a face recognition system.” IEEE Transactions on Information Forensics and Security 17 : 357-372 (2022).
[3] Sun, Zhaodong, and Xiaobai Li. “Privacy-phys: Facial video-based physiological modification for privacy protection.” IEEE Signal Processing Letters 29 : 1507-1511 (2022).
[4] Chen, Mingliang, Xin Liao, and Min Wu. “Pulse Edit: Editing physiological signals in facial videos for privacy protection.” IEEE Transactions on Information Forensics and Security 17 : 457-471 (2022).
[5] Zhong, Yaoyao, and Weihong Deng. “Opom: Customized invisible cloak towards face privacy protection.” IEEE Transactions on Pattern Analysis and Machine Intelligence 45, no. 3 : 3590-3603 (2022).
[6] Qiu, Yuying, Zhiyi Niu, Biao Song, Tinghuai Ma, Abdullah Al-Dhelaan, and Mohammed Al-Dhelaan. “A novel generative model for face privacy protection in video surveillance with utility maintenance.” Applied Sciences 12, no. 14 : 6962 (2022).
[7] Zhang, Xing, Seung-Hyun Seo, and Changda Wang. “A lightweight encryption method for privacy protection in surveillance videos.” IEEE Access 6 : 18074-18087 (2018).
[8] Lee, Donghyeok, and Namje Park. “Blockchain based privacy preserving multimedia intelligent video surveillance using secure Merkle tree.” Multimedia Tools and Applications 80 : 34517-34534 (2021).
[9] Kumar, Ankit, Pankaj Dadheech, Vijander Singh, Ramesh C. Poonia, and Linesh Raja. “An improved quantum key distribution protocol for verification.” Journal of Discrete Mathematical Sciences and Cryptography 22, no. 4 (2019).
[10] Andrew, Jane, and Max Baker. “The general data protection regulation in the age of surveillance capitalism.” Jnl of Business Ethics 168 : 565-578 (2021).
[11] Hosni Mahmoud, Hanan A., and Hanan Abdullah Mengash. “A novel technique for automated concealed face detection in surveillance videos.” Personal and Ubiquitous Computing 25 : 129-140 (2021).
[12] Cárdenas, Rolando J., Cesar A. Beltrán, and Juan C. Gutiérrez. “Small face detection using deep learning on surveillance videos.” Envi. 2, no. 5 : 14 (2019).
[13] Manju, D., and V. Radha. “A novel approach for pose invariant face recognition in surveillance videos.” Procedia Computer Science 167 : 890-899 (2020).
[14] Dong, Zuolin, Jiahong Wei, Xiaoyu Chen, and Pengfei Zheng. “Face detection in security monitoring based on artificial intelligence video retrieval technology.” IEEE Access 8 : 63421-63433 (2020).
[15] Ullah, Rehmat, Hassan Hayat, Afsah Abid Siddiqui, Uzma Abid Siddiqui, Jebran Khan, Farman Ullah, Shoaib Hassan et al. “A real-time framework for human face detection and recognition in cctv images.” Mathematical Problems in Engineering 2022 (2022).
[16] Kuang, Zhenzhong, Zhiqiang Guo, Jinglong Fang, Jun Yu, Noboru Babaguchi, and Jianping Fan. “Unnoticeable synthetic face replacement for image privacy protection.” Neurocomputing 457 : 322-333 (2021).
[17] Yang, Jingjing, Jiaxing Liu, Runkai Han, and Jinzhao Wu. “Transferable face image privacy protection based on federated learning and ensemble models.” Complex & Intelligent Systems 7, no. 5 (2021): 2299-2315.
[18] Davis, Simon. A recursion relation for the number of Goldbach partitions of an even integer, Journal of Discrete Mathematical Sciences and Cryptography, 27:1, 1–30 (2024), DOI: 10.47974/JDMSC-1188.
[19] Selikh, Bilel, Chillali, Abdelhakim, Mihoubi, Douadi & Ghadbane, Nacer. A new public key cryptosystem based on the non-commutative ring R, Journal of Discrete Mathematical Sciences and Cryptography, 27:1, 75–93 (2024), DOI: 10.47974/JDMSC-1573.
[20] Tuieb, Munthir Bahir, Serteep, Hind Jumaa & Ali, Doaa Muhsin Abed. Image steganography using Fresnelet transformations, stated coefficients and a pre-processed message, Journal of Discrete Mathematical Sciences and Cryptography, 26:6, 1683–1689 (2023), DOI: 10.47974/JDMSC-1614.

Views: 264Downloads: 11Citations: 2