Title :
Segmentation of Connected Symbols in Online Handwritten Chemical Formulas
Author :
Zhao, Lin ; Yan, Hu ; Shi, Guangshun ; Yang, Jufeng
Author_Institution :
Inst. of Machine Intell., Nankai Univ., Tianjin, China
Abstract :
In this paper, we present a novel approach to separate connected symbols in online handwritten chemical formulas. The proposed method combines both the chemical structural characteristics and online information. The main process can be divided into three stages: preprocessing, location of connected point, and segmentation. In addition, organic ring, a common chemical structure, is much different from other chemical symbols. We adopt the Freeman chain code to separate ring from chemical bond when they are connected. Experiment results show that the proposed method can not only satisfy the real-time demand, but also achieve a high correct segmentation rate of 92.7%.
Keywords :
chemical structure; handwritten character recognition; image segmentation; information networks; nomenclature; Freeman chain code; chemical structural characteristic; chemical structure; chemical symbol; connected symbol segmentation; online handwritten chemical formula; online information; organic ring; Algorithm design and analysis; Chemicals; Encoding; Handwriting recognition; IEEE Press; Image segmentation; Writing; Chemcial formulas; Connected symbols; Freeman chain code; Pen trace; Segmentation;
Conference_Titel :
System Science, Engineering Design and Manufacturing Informatization (ICSEM), 2010 International Conference on
Conference_Location :
Yichang
Print_ISBN :
978-1-4244-8664-9
DOI :
10.1109/ICSEM.2010.82
