PetroSeg

Description

PetroSeg is a user-friendly web application for unsupervised image segmentation, particularly optimized for thin section images and microscopic analysis. Developed with Streamlit and PyTorch, this application enables users to upload images, adjust segment colors, and download segmented outputs. The latest version incorporates TensorFlow and Tkinter for an enhanced, intuitive user interface. Please quote the app as follow: Azzam, F., Blaise, T., & Brigaud, B. (2024). Automated petrographic image analysis by supervised and unsupervised machine learning methods. Sedimentologika, 2(2). https://doi.org/10.57035/journals/sdk.2024.e22.1594

Resources

Name Format Description Link
57 https://www.data.gouv.fr/api/1/datasets/r/170adbda-2dfa-43dd-b3c0-c3b8c22756c7
57 https://www.data.gouv.fr/api/1/datasets/r/9f275bf6-58cb-49f3-b0d3-b378a7ead080
57 https://www.data.gouv.fr/api/1/datasets/r/acf8c046-3a9d-46ad-863b-11b15c741f0e

Tags

  • unsupervised-segmentation
  • image-segmentation
  • microscopy
  • thin-sections
  • image-analysis
  • petrology

Topics

Categories