作者: Peng Tang , Siu Cheung Hui , Chi-Wing Fu
关键词: Single bond 、 Chemical formula 、 Artificial intelligence 、 Computer science 、 Chemical structure 、 Connection (mathematics) 、 Topology 、 Bond 、 Handwriting recognition 、 Spatial complexity 、 Structural formula
摘要: Recognizing handwritten chemical structural formulas is challenging due to the spatial complexity involved, especially for skeletal formulas. In formulas, Carbon atoms are omitted in drawing of connected bonds, which single bonds with hidden as connection points. To recognize it important bond strokes and differentiate them from other similar symbols. Moreover, even if stroke identified, also split into several identify locations atoms, its positional relationship overall structure. this paper, we propose a progressive approach recognizing particular bonds. The proposed recognizes formula progressively while user draws formula.