Automatic Interpretation of Chemical Structure Diagrams

Chemical structure diagrams, just as in engineering drawings, maps, and other technical diagrams, consist of solid and dashed lines (bonds), characters (atom symbols), and other symbols such as brackets, parentheses, wedges (stereo-up bonds) or dashed wedges (stereo-down bonds). In addition to recognizing these low-level elements of such drawings, other artifacts may be present — bonds intersections may be crossings or atom nodes, character strings may represent underlying chemical structure, and circles are sometimes used to represent ring-alternating bonding — requiring a considerable knowledge base of chemistry to be able to interpret correctly. This paper discusses the general processes used in the program Kekule 1 that embodies this interpretation ability with more detailed explanations of how some problems relating to polygon approximation, dashed line and dashed wedge finding, and optical character recognition were solved.