Dynamic Amelioration of Resolution Mismatches for Local Feature Based Identity Inference

TL;DR

This paper introduces a dynamic framework that detects image resolution using local feature sensitivity and selects the optimal face recognition system, significantly improving accuracy across varying resolutions in surveillance scenarios.

Contribution

It proposes a novel resolution detection method based on local features that does not rely on image size, enabling dynamic selection of the best face recognition system for different resolutions.

Findings

Resolution detector achieves 99% accuracy in selecting appropriate systems.

Overall face recognition accuracy improves across multiple resolutions.

Framework outperforms individual baseline systems in experiments.

Abstract

While existing face recognition systems based on local features are robust to issues such as misalignment, they can exhibit accuracy degradation when comparing images of differing resolutions. This is common in surveillance environments where a gallery of high resolution mugshots is compared to low resolution CCTV probe images, or where the size of a given image is not a reliable indicator of the underlying resolution (eg. poor optics). To alleviate this degradation, we propose a compensation framework which dynamically chooses the most appropriate face recognition system for a given pair of image resolutions. This framework applies a novel resolution detection method which does not rely on the size of the input images, but instead exploits the sensitivity of local features to resolution using a probabilistic multi-region histogram approach. Experiments on a resolution-modified version of the "Labeled Faces in the Wild" dataset show that the proposed resolution detector frontend obtains a 99% average accuracy in selecting the most appropriate face recognition system, resulting in higher overall face discrimination accuracy (across several resolutions) compared to the individual baseline face recognition systems.