Difficulty in estimating visual information from randomly sampled images

TL;DR

This paper assesses how difficult it is to recover visual information from randomly sampled images, comparing it with traditional dimensionality reduction methods for privacy-preserving machine learning.

Contribution

It introduces an evaluation of random sampling as a privacy-preserving dimensionality reduction technique and compares its effectiveness with existing methods.

Findings

Random sampling has high difficulty in estimating original visual information.

Random sampling maintains spatial information invariance.

It performs comparably to traditional methods in image classification tasks.

Abstract

In this paper, we evaluate dimensionality reduction methods in terms of difficulty in estimating visual information on original images from dimensionally reduced ones. Recently, dimensionality reduction has been receiving attention as the process of not only reducing the number of random variables, but also protecting visual information for privacy-preserving machine learning. For such a reason, difficulty in estimating visual information is discussed. In particular, the random sampling method that was proposed for privacy-preserving machine learning, is compared with typical dimensionality reduction methods. In an image classification experiment, the random sampling method is demonstrated not only to have high difficulty, but also to be comparable to other dimensionality reduction methods, while maintaining the property of spatial information invariant.