Title: Licence plate redaction algorithm: a privacy-preserving approach

Authors: Divyanka Thakur; Bhagyalakshmi Vishwanath; Sonali Deshpande; Sunil S. Chavan

Addresses: Smt. Indira Gandhi College of Engineering, Plot No. 1, Sector 16, Ghansoli, Navi Mumbai, Maharashtra, 400701, India ' KC College of Engineering and Management Studies and Research, Mith Bunder Road, Near Sadguru Garden, Kopri, Thane (East), Maharashtra, 400603, India ' Smt. Indira Gandhi College of Engineering, Plot No. 1, Sector 16, Ghansoli, Navi Mumbai, Maharashtra, 400701, India ' Smt. Indira Gandhi College of Engineering, Plot No. 1, Sector 16, Ghansoli, Navi Mumbai, Maharashtra, 400701, India

Abstract: Licence plates are assigned to every vehicle for identification which displays unique letter-number combinations containing sensitive owner details. Redaction is masking of the sensitive information in media and is essential in surveillance to protect privacy. This research proposes an automated licence plate redaction system using NVIDIA DeepStream. Leveraging object detection and recognition models, the system identifies and redacts licence plates in realtime video footage. A dataset of various vehicles is compiled, annotated, and trained on YOLO-V5s, achieving 97% accuracy in licence plate detection. Integrated with DeepStream and PaddleOCR for recognition, a redaction algorithm applies anonymisation using Python's computer vision tools. The system ensures efficient, reliable licence plate redaction with minimal computational resource demands. Applicable in law enforcement, traffic analysis, parking, and toll systems, this tool enhances privacy and public safety while improving operational efficiency.

Keywords: licence plate redaction; NVIDIA Deepstream; Yolo model; PaddleOCR; artificial intelligence; video analytics; computer vision; object detection; deep learning.

DOI: 10.1504/IJAISC.2024.145620

International Journal of Artificial Intelligence and Soft Computing, 2024 Vol.8 No.3, pp.215 - 237

Received: 29 May 2023
Accepted: 14 May 2024
Published online: 09 Apr 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article