Kohulan/DECIMER-Image-Segmentation
Chemical structure detection and segmentation tool for Journal articles.
This tool helps chemists, researchers, and patent analysts automatically find and extract chemical structure images from scientific papers, patents, or scanned historical documents. You input a PDF document or an image of a page, and it outputs individual image files, each containing a precisely segmented chemical structure. It's designed for anyone needing to digitize large volumes of chemical knowledge.
138 stars.
Use this if you need to rapidly extract all chemical structure diagrams from scientific literature, patents, or scanned archives to build chemical databases or perform further analysis.
Not ideal if you only need to process a single, already isolated chemical structure image, or if you're looking for a tool to convert structures into SMILES strings directly (though this is a crucial first step for that).
Stars
138
Forks
36
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Feb 25, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Kohulan/DECIMER-Image-Segmentation"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
deepmodeling/deepmd-kit
A deep learning package for many-body potential energy representation and molecular dynamics
chemprop/chemprop
Message Passing Neural Networks for Molecule Property Prediction
mir-group/nequip
NequIP is a code for building E(3)-equivariant interatomic potentials
Acellera/moleculekit
MoleculeKit: Your favorite molecule manipulation kit
CederGroupHub/chgnet
Pretrained universal neural network potential for charge-informed atomistic modeling...