Lightweight Fault Detection and Management for Image Restoration
Cristiana Bolchini, Luca Cassano, Antonio Miele, Matteo Biasielli · 2020
Image restoration is generally employed to recover an image that has been blurred, for example, for noise suppression purposes. The Richardson-Lucy (RL) algorithm is a widely used iterative approach for image restoration. In this paper we propose a lightweight application-specific fault detection and management scheme for RL that exploits two specific characteristics of such algorithm: i) there is a strong correlation between the input and output images of each iteration, and ii) the algorithm is often able to produce a final output that is very similar to the expected one although the output of an intermediate iteration has been corrupted by a fault. The proposed scheme exploits these characteristics to detect the occurrence of a fault without requiring duplication and to determine whether the error in the output of an intermediate iteration of the algorithm would be absorbed (thus avoiding image dropping and algorithm reexecution) or whether the image has to be discarded and the overall elaboration to be re-executed. An experimental campaign demonstrated that our scheme allows for an execution time reduction of about 54% w.r.t. the classical Duplication with Comparison (DWC), still providing about 99% fault detection.