Masking Strategies for Image Manifolds
This addresses power efficiency in emerging imaging platforms by enabling compressive sensing through data-dependent masking, though it appears incremental as it builds on existing manifold learning and masking concepts.
The paper tackles the problem of selecting an optimal mask for image manifolds to reduce pixel acquisition in imaging sensors, showing that accurate manifold learning is possible with a subset of pixels, as demonstrated by numerical experiments preserving structure even with modest mask sizes.
We consider the problem of selecting an optimal mask for an image manifold, i.e., choosing a subset of the pixels of the image that preserves the manifold's geometric structure present in the original data. Such masking implements a form of compressive sensing through emerging imaging sensor platforms for which the power expense grows with the number of pixels acquired. Our goal is for the manifold learned from masked images to resemble its full image counterpart as closely as possible. More precisely, we show that one can indeed accurately learn an image manifold without having to consider a large majority of the image pixels. In doing so, we consider two masking methods that preserve the local and global geometric structure of the manifold, respectively. In each case, the process of finding the optimal masking pattern can be cast as a binary integer program, which is computationally expensive but can be approximated by a fast greedy algorithm. Numerical experiments show that the relevant manifold structure is preserved through the data-dependent masking process, even for modest mask sizes.