Dictionary and Image Recovery from Incomplete and Random Measurements

TL;DR

This paper presents a novel approach to dictionary learning from incomplete, random image measurements, demonstrating that spatial diversity in measurements guarantees unique solutions and accurate dictionary estimation for sparse image recovery.

Contribution

It introduces a theoretical framework that guarantees uniqueness and accuracy in dictionary learning from incomplete measurements without structural constraints.

Findings

Spatial diversity of measurements ensures solution uniqueness.

Modified dictionary learning algorithm accurately estimates the ideal dictionary.

Algorithm outperforms non-adaptive sparse recovery methods.

Abstract

This paper tackles algorithmic and theoretical aspects of dictionary learning from incomplete and random block-wise image measurements and the performance of the adaptive dictionary for sparse image recovery. This problem is related to blind compressed sensing in which the sparsifying dictionary or basis is viewed as an unknown variable and subject to estimation during sparse recovery. However, unlike existing guarantees for a successful blind compressed sensing, our results do not rely on additional structural constraints on the learned dictionary or the measured signal. In particular, we rely on the spatial diversity of compressive measurements to guarantee that the solution is unique with a high probability. Moreover, our distinguishing goal is to measure and reduce the estimation error with respect to the ideal dictionary that is based on the complete image. Using recent results from random matrix theory, we show that applying a slightly modified dictionary learning algorithm over compressive measurements results in accurate estimation of the ideal dictionary for large-scale images. Empirically, we experiment with both space-invariant and space-varying sensing matrices and demonstrate the critical role of spatial diversity in measurements. Simulation results confirm that the presented algorithm outperforms the typical non-adaptive sparse recovery based on offline-learned universal dictionaries.