A Framework for Dynamic Image Sampling Based on Supervised Learning (SLADS)

TL;DR

This paper introduces SLADS, a machine learning-based framework for dynamic image sampling that efficiently selects measurement points to reduce acquisition time and improve reconstruction quality.

Contribution

The paper proposes a fast, supervised learning approach for dynamic sampling that adapts to specific applications and extends to group sampling, outperforming static methods.

Findings

SLADS significantly reduces the number of measurements needed for high-quality image reconstruction.

The framework is computationally efficient and adaptable to different data types.

Experimental results show superior performance over existing static sampling techniques.

Abstract

Sparse sampling schemes have the potential to dramatically reduce image acquisition time while simultaneously reducing radiation damage to samples. However, for a sparse sampling scheme to be useful it is important that we are able to reconstruct the underlying object with sufficient clarity using the sparse measurements. In dynamic sampling, each new measurement location is selected based on information obtained from previous measurements. Therefore, dynamic sampling schemes have the potential to dramatically reduce the number of measurements needed for high fidelity reconstructions. However, most existing dynamic sampling methods for point-wise measurement acquisition tend to be computationally expensive and are therefore too slow for practical applications. In this paper, we present a framework for dynamic sampling based on machine learning techniques, which we call a supervised learning approach for dynamic sampling (SLADS). In each step of SLADS, the objective is to find the pixel that maximizes the expected reduction in distortion (ERD) given previous measurements. SLADS is fast because we use a simple regression function to compute the ERD, and it is accurate because the regression function is trained using data sets that are representative of the specific application. In addition, we introduce a method to terminate dynamic sampling at a desired level of distortion, and we extended the SLADS methodology to sample groups of pixels at each step. Finally, we present results on computationally-generated synthetic data and experimentally-collected data to demonstrate a dramatic improvement over state-of-the-art static sampling methods.