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

被引:2
作者
Sivalakshmi, Mallepogu [1 ]
Prasad, K. Rajendra [2 ]
Bindu, C. Shoba [1 ]
机构
[1] JNTUA Coll Engn, Dept Comp Sci & Engn, Ananthapuramu, Andhra Prades, India
[2] Inst Aeronaut Engn, Dept Comp Sci & Engn, Hyderabad, Telangana, India
关键词
Face identification; Privacy protection; Video surveillance; Convolutional neural network; Fire hawk's algorithm; Quality maintenance-variational autoencoders; RECOGNITION;
D O I
10.47974/JDMSC-1974
中图分类号
O29 [应用数学];
学科分类号
070104 ;
摘要
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
引用
收藏
页码:1205 / 1214
页数:10
相关论文
共 20 条
[1]   The General Data Protection Regulation in the Age of Surveillance Capitalism [J].
Andrew, Jane ;
Baker, Max .
JOURNAL OF BUSINESS ETHICS, 2021, 168 (03) :565-578
[2]  
Cardenas Rolando J, 2019, Envi, V2, P13
[3]   PulseEdit: Editing Physiological Signals in Facial Videos for Privacy Protection [J].
Chen, Mingliang ;
Liao, Xin ;
Wu, Min .
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2022, 17 :457-471
[4]   A recursion relation for the number of Goldbach partitions of an even integer [J].
Davis, Simon .
JOURNAL OF DISCRETE MATHEMATICAL SCIENCES & CRYPTOGRAPHY, 2024, 27 (01) :1-30
[5]   Face Detection in Security Monitoring Based on Artificial Intelligence Video Retrieval Technology [J].
Dong, Zuolin ;
Wei, Jiahong ;
Chen, Xiaoyu ;
Zheng, Pengfei .
IEEE ACCESS, 2020, 8 :63421-63433
[6]   Model Inversion Attack by Integration of Deep Generative Models: Privacy-Sensitive Face Generation From a Face Recognition System [J].
Khosravy, Mahdi ;
Nakamura, Kazuaki ;
Hirose, Yuki ;
Nitta, Naoko ;
Babaguchi, Noboru .
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2022, 17 :357-372
[7]   Unnoticeable synthetic face replacement for image privacy protection [J].
Kuang, Zhenzhong ;
Guo, Zhiqiang ;
Fang, Jinglong ;
Yu, Jun ;
Babaguchi, Noboru ;
Fan, Jianping .
NEUROCOMPUTING, 2021, 457 :322-333
[8]   Blockchain based privacy preserving multimedia intelligent video surveillance using secure Merkle tree [J].
Lee, Donghyeok ;
Park, Namje .
MULTIMEDIA TOOLS AND APPLICATIONS, 2021, 80 (26-27) :34517-34534
[9]   Power normalized cepstral robust features of deep neural networks in a cloud computing data privacy protection scheme [J].
Li, Mianjie ;
Tian, Zhihong ;
Du, Xiaojiang ;
Yuan, Xiaochen ;
Shan, Chun ;
Guizani, Mohsen .
NEUROCOMPUTING, 2023, 518 :165-173
[10]   A novel technique for automated concealed face detection in surveillance videos [J].
Mahmoud, Hanan A. Hosni ;
Mengash, Hanan Abdullah .
PERSONAL AND UBIQUITOUS COMPUTING, 2021, 25 (01) :129-140