Crossmark

Enhancing societal security: a multimodal deep learning approach for a public person identification and tracking system

Published Online: 2024-10-14

Authors

Yuvasini, D.

Jegadeesan, S.

Selvarajan, Shitharth

Mon, Feslin Anish
License Information

Text and Data Mining valid from 2024-10-14

Version of Record valid from 2024-10-14
More Information

Article History

Received: 27 May 2024

Accepted: 26 September 2024

First Online: 14 October 2024

Competing interests

: The authors declare no competing interests.

: All the human images used in this project are with the participant consent. The proposed system operates in public spaces, ethical and privacy concerns are paramount. The system integrates data from CCTV cameras and personal identifiers like Aadhar/SSN. To mitigate privacy risks, the system employs AES-secured communication, ensuring that personal identification data remains encrypted both at rest and in transit. Additionally, data processing only happens when necessary, ensuring that personal data are not stored or used without due cause, and images are anonymized before being used for feature extraction. Data access is restricted to authorized personnel, and strict consent protocols are followed for system use.

Document is current