A novel method for recognition of handwritten chemical symbols based on MQDF

Chemical symbols recognition is a base component in online handwritten chemical formulas recognition which has been paid more and more attention. This paper adopts 108 chemical symbols which are comprised of inorganic chemical symbols, organic ring structures, chemical bonds and laboratory apparatus. The recognizing process is divided into four steps. The first is adjusting and optimizing the handwritten data. Then, eight-directional features are extracted from each trajectory point. In the third stage, the features are optimized by maximum filter and Gaussian filter. The MQDF classifier is used for recognition of handwritten chemical symbols at last. Experimental results show that the proposed method is robust and flexible.