Cloud K-SVD for Image Denoising
This is an incremental improvement for image processing researchers, enabling distributed denoising with performance comparable to existing techniques.
The paper tackles image denoising by applying Cloud K-SVD, a distributed dictionary learning algorithm, to recover images from overlapping patches, achieving SSIM indices of 0.88, 0.91, and 0.95 for different noise levels, similar to state-of-the-art methods.
Cloud K-SVD is a dictionary learning algorithm that can train at multiple nodes and hereby produce a mutual dictionary to represent low-dimensional geometric structures in image data. We present a novel application of the algorithm as we use it to recover both noiseless and noisy images from overlapping patches. We implement a node network in Kubernetes using Docker containers to facilitate Cloud K-SVD. Results show that Cloud K-SVD can recover images approximately and remove quantifiable amounts of noise from benchmark gray-scaled images without sacrificing accuracy in recovery; we achieve an SSIM index of 0.88, 0.91 and 0.95 between clean and recovered images for noise levels ($μ$ = 0, $σ^{2}$ = 0.01, 0.005, 0.001), respectively, which is similar to SOTA in the field. Cloud K-SVD is evidently able to learn a mutual dictionary across multiple nodes and remove AWGN from images. The mutual dictionary can be used to recover a specific image at any of the nodes in the network.