DECIMER Logo

DECIMER.ai

An open platform for automated optical chemical structure identification, segmentation and recognition in scientific publications.

How to use the DECIMER web app

Just upload a PDF document or one or multiple images that contain chemical structure depictions. If a PDF document is uploaded, DECIMER Segmentation is used to detect and segment all chemical structure depictions. The detected or uploaded chemical structure depictions are processed using the powerful OCSR engine of DECIMER V2. The chemical structure depictions and the corresponding SMILES representation are presented for your review.

You can edit the structures according to your needs in the Ketcher chemical structure editor windows before downloading the segmented images and the corresponding mol files. Additionally, the IUPAC names of the chemical structures can be resolved using STOUT V2.

About DECIMER

Deep Learning for Chemical Image Recognition (DECIMER) is a step towards automated chemical image segmentation and recognition. DECIMER is actively developed and maintained by the Steinbeck group at the Friedrich Schiller University Jena.

You need to have the right granted by the publisher of the uploaded documents and images to use them for data mining. We do not store or use the data for anything other than automated processing and display of results in the web app. Your documents and images are only saved for one hour unless a problem is reported. If a problem is reported, we will use the reported image to analyse errors before deleting them.

Google Analytics is used to get some basic statistics about the number of visitors. You can look up a more detailed description of what happens with your data in our privacy policy. German law requires us to provide some information about who we are: Impressum - Legal Disclosure.