@article{Docherty:2024:10.21105/joss.06159,
author = {Docherty, R and Squires, I and Vamvakeros, A and Cooper, SJ},
doi = {10.21105/joss.06159},
journal = {Journal of Open Source Software},
pages = {6159--6159},
title = {SAMBA: a trainable segmentation web-app with smart labelling},
url = {http://dx.doi.org/10.21105/joss.06159},
volume = {9},
year = {2024}
}

Download

TY  - JOUR
AB  - 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 characterisation. 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. Trainablesegmentation 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 arandom forest classifier for robust, generalisable 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 powerfulhardware.
AU  - Docherty,R
AU  - Squires,I
AU  - Vamvakeros,A
AU  - Cooper,SJ
DO  - 10.21105/joss.06159
EP  - 6159
PY  - 2024///
SN  - 2475-9066
SP  - 6159
TI  - SAMBA: a trainable segmentation web-app with smart labelling
T2  - Journal of Open Source Software
UR  - http://dx.doi.org/10.21105/joss.06159
UR  - http://hdl.handle.net/10044/1/112659
VL  - 9
ER  - 

Download