U-SLADS: Unsupervised Learning Approach for Dynamic Dendrite Sampling
This work addresses a domain-specific challenge in materials science for researchers needing efficient imaging of metal dendrites, representing an incremental improvement over existing supervised methods.
The paper tackles the problem of dynamic sparse sampling for imaging skeleton-like metal dendrites, proposing an unsupervised learning approach using Hierarchical Gaussian Mixture Models (HGMM) to enable fast imaging of primary and secondary arms during solidification processes.
Novel data acquisition schemes have been an emerging need for scanning microscopy based imaging techniques to reduce the time in data acquisition and to minimize probing radiation in sample exposure. Varies sparse sampling schemes have been studied and are ideally suited for such applications where the images can be reconstructed from a sparse set of measurements. Dynamic sparse sampling methods, particularly supervised learning based iterative sampling algorithms, have shown promising results for sampling pixel locations on the edges or boundaries during imaging. However, dynamic sampling for imaging skeleton-like objects such as metal dendrites remains difficult. Here, we address a new unsupervised learning approach using Hierarchical Gaussian Mixture Mod- els (HGMM) to dynamically sample metal dendrites. This technique is very useful if the users are interested in fast imaging the primary and secondary arms of metal dendrites in solidification process in materials science.