Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

SAMBA: A Trainable Segmentation Web-App with Smart Labelling

Ronan Docherty, Isaac Squires, Antonis Vamvakeros, Samuel J. Cooper

Abstract

Segmentation is the assigning of a semantic class to every pixel in an image and is a prerequisite for various statistical analysis tasks in materials science, like phase quantification, physics simulations or morphological characterization. The wide range of length scales, imaging techniques and materials studied in materials science means any segmentation algorithm must generalise to unseen data and support abstract, user-defined semantic classes. Trainable segmentation is a popular interactive segmentation paradigm where a classifier is trained to map from image features to user drawn labels. SAMBA is a trainable segmentation tool that uses Meta's Segment Anything Model (SAM) for fast, high-quality label suggestions and a random forest classifier for robust, generalizable segmentations. It is accessible in the browser (https://www.sambasegment.com/) without the need to download any external dependencies. The segmentation backend is run in the cloud, so does not require the user to have powerful hardware.

SAMBA: A Trainable Segmentation Web-App with Smart Labelling

Abstract

Segmentation is the assigning of a semantic class to every pixel in an image and is a prerequisite for various statistical analysis tasks in materials science, like phase quantification, physics simulations or morphological characterization. The wide range of length scales, imaging techniques and materials studied in materials science means any segmentation algorithm must generalise to unseen data and support abstract, user-defined semantic classes. Trainable segmentation is a popular interactive segmentation paradigm where a classifier is trained to map from image features to user drawn labels. SAMBA is a trainable segmentation tool that uses Meta's Segment Anything Model (SAM) for fast, high-quality label suggestions and a random forest classifier for robust, generalizable segmentations. It is accessible in the browser (https://www.sambasegment.com/) without the need to download any external dependencies. The segmentation backend is run in the cloud, so does not require the user to have powerful hardware.
Paper Structure (2 sections, 1 figure)

This paper contains 2 sections, 1 figure.

Table of Contents

  1. Statement of Need
  2. Design and Usage

Figures (1)

  • Figure 1: (a) a screenshot of the GUI of SAMBA, highlighting the different possible labelling types. (b) shows the impact of changing the 'Smart Labelling' scale parameter for the same cursor location, enabling fine-grained segmentation of small objects or rapid segmentation of large phases. (c) the resulting multi-phase segmentation from the random forest backend.