ChemPix: automated recognition of hand-drawn hydrocarbon structures using deep learning

Abstract

Offline recognition of hand-drawn hydrocarbon structures is learned using an image-to-SMILES neural network through the application of synthetic data generation and ensemble learning.

Document Details

• Document Type: Pub Defense Publication
• Publication Date: Jan 01, 2021
• Source ID: 10.1039/d1sc02957f

Entities

People

• Amelia Woodward
• Augustin Braun
• Benjamin Choi
• Hayley Weir
• Keiran C Thompson
• Todd Martinez

Organizations

• Office of Naval Research
• SLAC National Accelerator Laboratory
• Stanford University
• United States Army
• Yusuf Hamied Department of Chemistry

Tags

Fields of Study

• Computer science

Readers

• Computer Science/Computer Engineering/Data Science/Digital Signal Processing.
• Groundwater Contamination Remediation.
• Neural Network Machine Learning.

Technology Areas

• AI & ML
• AI & ML - Neural Networks