FRIST - Flipping and Rotation Invariant Sparsifying Transform Learning and Applications
This work addresses the need for efficient and invariant sparse representation in signal processing and computer vision, though it appears incremental as it builds on existing transform learning methods.
The paper tackled the problem of representing natural images with textures in various directions by developing FRIST, a flipping and rotation invariant sparsifying transform learning method, which showed promising performance in tasks like image representation, denoising, and MRI reconstruction.
Features based on sparse representation, especially using the synthesis dictionary model, have been heavily exploited in signal processing and computer vision. However, synthesis dictionary learning typically involves NP-hard sparse coding and expensive learning steps. Recently, sparsifying transform learning received interest for its cheap computation and its optimal updates in the alternating algorithms. In this work, we develop a methodology for learning Flipping and Rotation Invariant Sparsifying Transforms, dubbed FRIST, to better represent natural images that contain textures with various geometrical directions. The proposed alternating FRIST learning algorithm involves efficient optimal updates. We provide a convergence guarantee, and demonstrate the empirical convergence behavior of the proposed FRIST learning approach. Preliminary experiments show the promising performance of FRIST learning for sparse image representation, segmentation, denoising, robust inpainting, and compressed sensing-based magnetic resonance image reconstruction.