Abstract: The segmentation algorithm of chemical molecular structure based on area size and bending degree was proposed to segment chemical bonds, heteroatoms and perssad. First, chemical molecular structure images were segmented into two parts according to connection area size. One was the combination of all big size connection areas containing chemical bonds, and the other was the combination of heteroatoms, perssad and single chemical bonds. Second, single lines were extracted based on bending degree, which represents small size combination images, and likelines such as “I”,“l” and “-”. Finally, “I”,“l”, “-” and single lines were distinguished, chemical bonds of single lines and big size connection areas were combined, and the segmentation of chemical bonds, heteroatoms and perssad was realized. The accuracy by the proposed algorithm reached to 983％, and the segmentation effect was consistent with human visual perception. This is the foundation for automatically extracting chemical molecular structure images.

Key words: chemical molecular structure images, image segmentation, area size, bending degree, chemical bond, atom