Our recent research article on DECIMER.ai has been published in Nature Communications. DECIMER is an open-source platform that harnesses recent progress in deep learning, computer vision, and natural language processing. Its primary purpose is to autonomously segment, classify, and translate chemical structure depictions found in printed literature into a machine-readable file format. The segmentation and classification tools are the only openly available packages of their kind, while the core application for optical chemical structure recognition (OCSR) delivers exceptional performance across all benchmark datasets. The source code, the trained models and the datasets developed in this work have been published under permissive licences.
Rajan, K., Brinkhaus, H.O., Agea, M.I. et al. DECIMER.ai: an open platform for automated optical chemical structure identification, segmentation and recognition in scientific publications. Nat Commun 14, 5045 (2023).