Adaptive Denoising and Alignment Agents for Infrared Imaging
Vito M. Leli, Viktor Shipitsin, Oleg Y. Rogov, A. Sarachakov, Dmitry V. Dylov · IEEE Control Systems Letters · 2021
Clinical infrared imagers, such as those used to visualize subcutaneous vasculature, rely on the image-projection feedback loops. Specifically, these instruments embed model-based feedback algorithms to process the acquired ’invisible’ infrared data streams and then to project a visible copy of them back to the imaged region (e.g., the skin of the patient’s forearm). Being inherently noisy, the infrared frames and their projections are prone to misalignment, demanding frequent instrument tuning and recalibration. To address this challenge, we propose to reconsider the feedback loop entailed in such imagers from the standpoint of multi-agent deep learning. Both proposed agents –DenoiserandAligner– are adaptive in that they continuously optimize the corresponding target value functions. Namely, theDenoiserlearns the proper frequency decomposition of the acquired infrared data until the target segmentation metric is maximized; whereas, theAlignerlearns the intensity fluctuations within the segmentation mask tuned by theDenoiseruntil its maximal overlap with the source infrared image. The idea is validated synthetically on a benchmark dataset and experimentally on a bench-top vein scanner in the lab, with the duet of agents proving efficient in handling the distortions and the misalignment.