Face enhancement and recognition system improves CCTV surveillance quality
CVBL-CCTV-Face Dataset for Real-World Face Enhancement and Recognition in Surveillance
Computer Vision and Pattern Recognition
Summary
Faces captured by security cameras often look unclear because of low resolution, blurring, and other problems, making it hard to recognize people. The authors created a dataset pairing fuzzy surveillance face images with clear photos taken under good conditions. They built a step-by-step system that detects faces, makes the images clearer using AI, and then identifies the person by comparing unique digital face features. Their approach works in real-time and in uncontrolled environments like typical camera footage.
What this means in practice
- •For security system developers: Use enhanced face images from low-quality CCTV footage to improve real-time identity verification in surveillance environments.$Commercial implications: Enables building better commercial face recognition products that work with existing security cameras by improving image clarity and recognition accuracy.
- •For law enforcement image analysts: Assist analysis of poor-quality surveillance images by generating higher-resolution faces linked to known references for better identification.
Authors
Manish Das, Ajay Kumar Yadav, Shiv Ram Dubey, Satish Kumar Singh
Abstract
In real-world surveillance settings, facial captures from closed-circuit television systems suffer from degradations such as low resolution, motion blur, noise, and occlusions, which undermine dependable face recognition. In this study, we propose a framework for super-resolution and identity recognition, aimed at surveillance applications. For this purpose, we present the CVBL-CCTV-Face Dataset which is a dataset of real-world images taken in an unpaired manner where each pair consists of a low-quality (LQ) image of a face captured by a 8MP IP Dome CCTV camera together with a high-quality (HQ) reference image that is taken in controlled settings. In order to cope with the various problems posed by such datasets, we construct a modular system that involves face detection, deep learning-based super-resolution of low-quality face images, and identity recognition through L2-normalized embeddings extracted by an embedding model. Enhancement models are trained and tested according to three different setups, and the system is deployed for identity verification in a real-time unconstrained environment.