@unpublished{RajanBrinkhausZielesnyetal.2024, author = {Rajan, Kohulan and Brinkhaus, Henning Otto and Zielesny, Achim and Steinbeck, Christoph}, title = {Advancements in Hand-Drawn Chemical Structure Recognition through an Enhanced DECIMER Architecture}, doi = {10.26434/chemrxiv-2024-7ch9f}, year = {2024}, abstract = {Accurate recognition of hand-drawn chemical structures is crucial for digitising hand-written chemical information found in traditional laboratory notebooks or for facilitating stylus-based structure entry on tablets or smartphones. However, the inherent variability in hand-drawn structures poses challenges for existing Optical Chemical Structure Recognition (OCSR) software. To address this, we present an enhanced Deep lEarning for Chemical ImagE Recognition (DECIMER) architecture that leverages a combination of Convolutional Neural Networks (CNNs) and Transformers to improve the recognition of hand-drawn chemical structures. The model incorporates an EfficientNetV2 CNN encoder that extracts features from hand-drawn images, followed by a Transformer decoder that converts the extracted features into Simplified Molecular Input Line Entry System (SMILES) strings. Our models were trained using synthetic hand-drawn images generated by RanDepict, a tool for depicting chemical structures with different style elements. To evaluate the model's performance, a benchmark was performed using a real-world dataset of hand-drawn chemical structures. The results indicate that our improved DECIMER architecture exhibits a significantly enhanced recognition accuracy compared to other approaches.}, language = {en} } @article{RajanBrinkhausSteinbecketal.2024, author = {Rajan, Kohulan and Brinkhaus, Henning Otto and Steinbeck, Christoph and Zielesny, Achim}, title = {Advancements in hand-drawn chemical structure recognition through an enhanced DECIMER architecture}, series = {Journal of Cheminformatics}, volume = {2024}, journal = {Journal of Cheminformatics}, number = {16: 78}, doi = {10.1186/s13321-024-00872-7}, year = {2024}, abstract = {Accurate recognition of hand-drawn chemical structures is crucial for digitising hand-written chemical information in traditional laboratory notebooks or facilitating stylus-based structure entry on tablets or smartphones. However, the inherent variability in hand-drawn structures poses challenges for existing Optical Chemical Structure Recognition (OCSR) software. To address this, we present an enhanced Deep lEarning for Chemical ImagE Recognition (DECIMER) architecture that leverages a combination of Convolutional Neural Networks (CNNs) and Transformers to improve the recognition of hand-drawn chemical structures. The model incorporates an EfficientNetV2 CNN encoder that extracts features from hand-drawn images, followed by a Transformer decoder that converts the extracted features into Simplified Molecular Input Line Entry System (SMILES) strings. Our models were trained using synthetic hand-drawn images generated by RanDepict, a tool for depicting chemical structures with different style elements. A benchmark was performed using a real-world dataset of hand-drawn chemical structures to evaluate the model's performance. The results indicate that our improved DECIMER architecture exhibits a significantly enhanced recognition accuracy compared to other approaches.}, language = {en} }