Human-Imperceptible Identification with Learnable Lensless Imaging

TL;DR

This paper introduces a learnable lensless imaging system that balances visual privacy and recognition accuracy by producing human-imperceptible images while retaining machine-recognizable information, validated through simulation and hardware implementation.

Contribution

The authors propose a novel framework with specialized loss functions to achieve privacy-preserving lensless imaging without sacrificing recognition performance.

Findings

Images are rendered imperceptible to humans but still recognizable by machines.

The framework effectively balances privacy protection and recognition accuracy.

Hardware implementation confirms the practical viability of the approach.

Abstract

Lensless imaging protects visual privacy by capturing heavily blurred images that are imperceptible for humans to recognize the subject but contain enough information for machines to infer information. Unfortunately, protecting visual privacy comes with a reduction in recognition accuracy and vice versa. We propose a learnable lensless imaging framework that protects visual privacy while maintaining recognition accuracy. To make captured images imperceptible to humans, we designed several loss functions based on total variation, invertibility, and the restricted isometry property. We studied the effect of privacy protection with blurriness on the identification of personal identity via a quantitative method based on a subjective evaluation. Moreover, we validate our simulation by implementing a hardware realization of lensless imaging with photo-lithographically printed masks.