Automatic Recognition of Chemical Images

Abstract

Images of chemical molecules can be produced, manipulated, simulated and analyzed using sophisticated chemical software. However, in the process of publishing such images into scientific literature, all their chemical significance is lost. Although images of chemical molecules can be easily analyzed by the human expert, they cannot be fed back into chemical software and loose much of their potential use. We have developed a system that can automatically reconstruct the chemical information associated to the images of chemical molecules thus rendering them computer readable. We have benchmarked our system against a commercially available product and have also tested it using chemical databases of several thousand images with very encouraging results.

Chemical structure recognition: a rule-based approach

“…One neighbour of any internal element must be strictly longer than the internal element, the other neighbour must be strictly shorter. 6. Length of elements of L is strictly monotonically increasing from e l to e u .…”

“…No two elements of L have a separation distance of less than the minimum of ds. 6. Two elements of L, called end elements, dash-neighbour wrt.…”

“…15 Thus the recognition process is usually based on a set of heuristics that need to be experimentally tuned. The only exception appears to be the chemOCR project, 6,7 which claims to apply a rule based approach within an expert system to reconstruct the molecule description from graph and character information of the molecule structure. However, from the literature it is unclear how this rule based approach works or what the single rules would be.…”

Recognition a Hand Drawn Chemical Structure Diagrams Using the Discrete B-Spline Wavelet Transform

“…This method include a cleaning method to tie any lines destroyed close to an intersection (so quite two lines halve) and to proper any elementary lines be divided into smaller pieces [15]. To valid the primary situation, any comparatively teeny lines are deleted and also the lines linked to them are joined.…”

“…Another situation is treated by employing a predetermined worth for the investor at the purpose wherever two lines link. If whether lines are instituted to form an investor below the threshold chose, the purpose of gathering is extracted and also the two lines are integrated to formulate long-term line section [15].…”