In digital image processing and computer vision, image segmentation refers to the process of partitioning a digital image into multiple segments or related sets of pixels. This tutorial introduces you to U-Net, a popular convolutional neural network commonly developed for image segmentation in biomedicine. Using an assembled data set, you will learn how to create and train a U-Net neural network, and apply it to segment scanning electron microscopy images of graphene on a substrate.

The nanoHUB tool "SEM Image Segmentation Workshop" used in this hands-on tutorial.

Network for Computational Nanotechnology (NCN)

Researchers should cite this work as follows:

• Aagam Rajeev Shah (2021), "U-Net Convolutional Neural Networks for Image Segmentation: Application to Scanning Electron Microscopy Images of Graphene," https://nanohub.org/resources/34744.

  BibTex | EndNote

1. Biomedicine
2. convolutional neural networks (CNN)
3. graphene
4. hands on
5. image processing
6. image segmentation
7. machine learning
8. materials science
9. nano/bio
10. nanoMFG Node
11. NCN Group - Machine Learning
12. NCN Group - Machine Learning Hands-on
13. neural networks
14. scanning electron microscopy (SEM)
15. tutorial