English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Accurate and efficient extraction of microstructures in microscopic images ofmaterials plays a critical role in the exploration of structure-propertyrelationships and the optimization of process parameters. Deep learning-basedimage segmentation techniques that rely on manual annotation are time-consumingand labor-intensive and hardly meet the demand for model transferability andgeneralization. Segment Anything Model (SAM), a large visual model withpowerful deep feature representation and zero-shot generalization capabilities,has provided new solutions for image segmentation. However, directly applyingSAM to segmenting microstructures in microscopic images of materials withouthuman annotation cannot achieve the expected results, as the difficulty ofadapting its native prompt engineering to the dense and dispersedcharacteristics of key microstructures in materials microscopy images. In thispaper, we propose MatSAM, a general and efficient microstructure extractionsolution based on SAM. A new point-based prompts generation strategy isdesigned, grounded on the distribution and shape of materials microstructures.It generates prompts for different microscopic images, fuses the prompts of theregion of interest (ROI) key points and grid key points, and integratespost-processing methods for quantitative characterization of materialsmicrostructures. For common microstructures including grain boundary and phase,MatSAM achieves superior segmentation performance to conventional methods andis even preferable to supervised learning methods evaluated on 18 materialsmicrostructures imaged by the optical microscope (OM) and scanning electronmicroscope (SEM). We believe that MatSAM can significantly reduce the cost ofquantitative characterization of materials microstructures and accelerate thedesign of new materials.

MatSAM: Efficient Materials Microstructure Extraction via Visual Large Model