An image compression and encryption scheme based on deep learning

TL;DR

This paper proposes a novel image compression and encryption scheme using stacked auto-encoders for data reduction and chaotic logistic maps for security, demonstrating its feasibility and effectiveness for internet image transmission and protection.

Contribution

It introduces a combined deep learning and chaos theory approach for simultaneous image compression and encryption, which is a novel application in this domain.

Findings

The scheme effectively compresses images with deep auto-encoders.

The encryption using chaotic logistic maps enhances security.

Experimental results confirm the method's feasibility and efficiency.

Abstract

Stacked Auto-Encoder (SAE) is a kind of deep learning algorithm for unsupervised learning. Which has multi layers that project the vector representation of input data into a lower vector space. These projection vectors are dense representations of the input data. As a result, SAE can be used for image compression. Using chaotic logistic map, the compression ones can further be encrypted. In this study, an application of image compression and encryption is suggested using SAE and chaotic logistic map. Experiments show that this application is feasible and effective. It can be used for image transmission and image protection on internet simultaneously.