Reconstruction of Chemical Molecules from Images

Abstract

We have developed a system for the automatic reconstruction of chemical molecules from images. The system takes as input an electronically produced image of a chemical molecule and produces an SDF file containing the complete chemical description of the molecule. The SDF file can then be read and used by most chemical computer programs. Our system finds extensive application in information extraction problems where the molecule images contained in chemical documents need to be rendered computer readable. We have benchmarked our system against a commercially available product and have also tested it using chemical databases of several thousand images. The system can be parameterized to reconstruct images of different sources and different characteristics.

Chemical structure recognition: a rule-based approach

“…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.…”

ChemEx: information extraction system for chemical data curation

“…Existing techniques for the chemical information extraction can be broadly classified into two categories: visual and textual data extraction. The visual data extraction system, such as Kekulé [7], CLiDE [8,9], chemOCR [10], OSRA [11], and ChemReader [12], focuses on interpretation of images embedded in documents while the textual data extraction focuses on mining interested entities and their relations from text. Textual data extraction is varied based on a subject domain, such as chemical names [13,14], chemical formulae [14], or drug names [15].…”

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

“…Characters and others of comparatively larger magnitude may be understood not withstanding their magnitude and font and also its rotation [14]. Once distinguishing symbols, they are distributed by the tow directions in step with their coordinates to create statement that are successively during seek in a database of considerably utilized feasible groups such as R-groups and other ones.…”

“…The attached part streams of collections distributing as letters that won't to restore their identical element collection from the image shape that successively square measure that is used as input to the optical character into their authentic requisite construction style. Uncommented strings are neglected [14].…”

“…Given a stroke sequence (o1, o2,…,oN) of N round, the objective of image gathering is to search out the best image sequence (G1, G2,…,Gn) with corresponding boundaries within the most probability sense [14].…”