Optical Chemical Structure Recognition

Transformer-based OCSR using a novel synthetic data generation pipeline for robust molecular image interpretation across …

Encoder-decoder model using pre-trained ResNet and attention-based LSTM to translate molecular images into SMILES, …

Deep learning OCSR tool using YOLOv5 and MobileNetV2 to extract machine-readable molecular structures from scientific …

Patch-based CNN method for detecting Markush structures in chemical images, addressing low signal-to-noise ratios in …

Systematization of OCSR evolution from rule-based systems to deep learning, highlighting the paradigm shift to image …

Ablation study comparing SMILES, DeepSMILES, SELFIES, and InChI for OCSR. SMILES achieves highest accuracy; SELFIES …

Deep learning model using Swin Transformer and Focal Loss for OCSR, achieving 98.58% accuracy on synthetic benchmarks.

Deep learning OCSR method using semantic segmentation and classification CNNs to reconstruct chemical graphs with …

Deep learning method for optical chemical structure recognition using image captioning networks trained on millions of …

An end-to-end deep learning approach using U-Net and CNN-LSTM to segment and predict chemical structures from document …

A two-phase neural network approach for recognizing handwritten heterocyclic chemical rings with ~94% accuracy.

A hybrid SVM and elastic matching approach for recognizing handwritten chemical symbols drawn on touch devices, …