Filtern
Erscheinungsjahr
Dokumenttyp
- Wissenschaftlicher Artikel (1112)
- Konferenzveröffentlichung (351)
- Teil eines Buches (Kapitel) (322)
- Beitrag zu einer (nichtwissenschaftlichen) Zeitung oder Zeitschrift (237)
- Buch (Monographie) (219)
- Bericht (75)
- Video (60)
- Sonstiges (47)
- Vorlesung (46)
- Rezension (27)
Sprache
- Deutsch (1987)
- Englisch (572)
- Französisch (4)
- Mehrsprachig (2)
- Spanisch (2)
- Rumänisch (1)
Schlagworte
- Robotik (30)
- Flugkörper (21)
- UAV (21)
- Journalismus (15)
- Bionik (11)
- Rettungsrobotik (8)
- 3D Modell (7)
- Akkreditierung (7)
- E-Learning (7)
- Juristenausbildung (7)
Institut
- Wirtschaftsrecht (835)
- Institut für Internetsicherheit (262)
- Wirtschaft und Informationstechnik Bocholt (254)
- Informatik und Kommunikation (220)
- Institut für Innovationsforschung und -management (194)
- Westfälisches Institut für Gesundheit (141)
- Westfälisches Energieinstitut (106)
- Wirtschaft Gelsenkirchen (65)
- Maschinenbau Bocholt (60)
- Elektrotechnik und angewandte Naturwissenschaften (59)
Advancements in Hand-Drawn Chemical Structure Recognition through an Enhanced DECIMER Architecture
(2024)
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.