eduzhai > Applied Sciences > Engineering >

Improving the Segmentation of Scanning Probe Microscope Images using Convolutional Neural Networks

  • king
  • (0) Download
  • 20210507
  • Save

... pages left unread,continue reading

Document pages: 21 pages

Abstract: A wide range of techniques can be considered for segmentation of images ofnanostructured surfaces. Manually segmenting these images is time-consuming andresults in a user-dependent segmentation bias, while there is currently noconsensus on the best automated segmentation methods for particular techniques,image classes, and samples. Any image segmentation approach must minimise thenoise in the images to ensure accurate and meaningful statistical analysis canbe carried out. Here we develop protocols for the segmentation of images of 2Dassemblies of gold nanoparticles formed on silicon surfaces via deposition froman organic solvent. The evaporation of the solvent drives far-from-equilibriumself-organisation of the particles, producing a wide variety of nano- andmicro-structured patterns. We show that a segmentation strategy using the U-Netconvolutional neural network outperforms traditional automated approaches andhas particular potential in the processing of images of nanostructured systems.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×