Difficulty in estimating visual information from randomly sampled images
This work addresses the problem of protecting visual information for privacy-preserving machine learning by evaluating the difficulty of reconstructing original images from dimensionally reduced data.
This paper evaluates dimensionality reduction methods, specifically random sampling, for their difficulty in estimating original visual information from reduced images. The random sampling method demonstrated high difficulty in visual information estimation while maintaining spatial information invariance and performing comparably to other dimensionality reduction methods in image classification.
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.