@unpublished{BrinkhausZielesnySteinbecketal.2022, author = {Brinkhaus, Henning Otto and Zielesny, Achim and Steinbeck, Christoph and Rajan, Kohulan}, title = {DECIMER - Hand-drawn molecule images dataset}, year = {2022}, abstract = {The translation of images of chemical structures into machine-readable representations of the depicted molecules is known as optical chemical structure recognition (OCSR). There has been a lot of progress over the last three decades in this field, but the development of systems for the recognition of complex hand-drawn structure depictions is still at the beginning. Currently, there is no data for the systematic evaluation of OCSR methods on hand-drawn structures available. Here we present DECIMER - Hand-drawn molecule images, a standardised, openly available benchmark dataset of 5088 hand-drawn depictions of diversely picked chemical structures. Every structure depiction in the dataset is mapped to a machine-readable representation of the underlying molecule. The dataset is openly available and published under the CC-BY 4.0 licence which applies very few limitations. We hope that it will contribute to the further development of the field.}, language = {en} }