Revealing Quantum Information Encoded in Classical Images

TL;DR

This paper explores a quantum pre-processing filter with two CNOT gates for image feature extraction, assessing its impact on classical neural network classification and its potential to capture pixel correlations beyond classical filters.

Contribution

Introduces a simple quantum filter circuit with two CNOT gates for image feature extraction, analyzing its effects and potential in classical neural network architectures.

Findings

Small quantum circuit improves classification with simple networks

No clear correlation between entanglement level and performance gain

Potential for enhancement in more advanced architectures

Abstract

In this study, we investigate a simple quantum pre-processing filter kernel designed with only two CNOT gates for image feature extraction. We examine the impact of these filters when combined with a classical neural network for image classification tasks. Our main hypothesis is that this circuit can extract pixel correlation information that classical filters cannot. This approach is akin to a convolutional neural network, but with quantum layers replacing convolutional layers to extract spatial pixel entanglement. We found that a small circuit with just two CNOT gates can be engineered in three different spatial symmetries, each affecting classification differently. While the filter improves classification when combined with a simple, narrow network, it does not surpass complex classical methods. However, the filter demonstrates potential to enhance classification performance in more sophisticated architectures. Despite this, our empirical results show no clear correlation between the observed improvements and the level of entanglement in the quantum circuit, as measured by Von Neumann Entropy. The underlying cause of this improvement remains unclear and warrants further investigation.