%0 Journal Article %1 Filippov2009 %A Filippov, Igor %A Nicklaus, Marc %B Journal of Chemical Information and Modeling %D 2009 %I American Chemical Society %J Journal of Chemical Information and Modeling %K chemical-information chemical-structures oclcml open-source optical-structure-recognition osra %N 3 %P 740--743 %R 10.1021/ci800067r %T Optical structure recognition software to recover chemical information: OSRA, an open source solution. %U http://dx.doi.org/10.1021/ci800067r %V 49 %X Until recently most scientific and patent documents dealing with chemistry have described molecular structures either with systematic names or with graphical images of Kekulé structures. The latter method poses inherent problems in the automated processing that is needed when the number of documents ranges in the hundreds of thousands or even millions since graphical representations cannot be directly interpreted by a computer. To recover this structural information, which is otherwise all but lost, we have built an optical structure recognition application based on modern advances in image processing implemented in open source tools, OSRA. OSRA can read documents in over 90 graphical formats including GIF, JPEG, PNG, TIFF, PDF, and PS, automatically recognizes and extracts the graphical information representing chemical structures in such documents, and generates the SMILES or SD representation of the encountered molecular structure images. Until recently most scientific and patent documents dealing with chemistry have described molecular structures either with systematic names or with graphical images of Kekulé structures. The latter method poses inherent problems in the automated processing that is needed when the number of documents ranges in the hundreds of thousands or even millions since graphical representations cannot be directly interpreted by a computer. To recover this structural information, which is otherwise all but lost, we have built an optical structure recognition application based on modern advances in image processing implemented in open source tools, OSRA. OSRA can read documents in over 90 graphical formats including GIF, JPEG, PNG, TIFF, PDF, and PS, automatically recognizes and extracts the graphical information representing chemical structures in such documents, and generates the SMILES or SD representation of the encountered molecular structure images.

@article{Filippov2009, abstract = {{Until recently most scientific and patent documents dealing with chemistry have described molecular structures either with systematic names or with graphical images of Kekul\'{e} structures. The latter method poses inherent problems in the automated processing that is needed when the number of documents ranges in the hundreds of thousands or even millions since graphical representations cannot be directly interpreted by a computer. To recover this structural information, which is otherwise all but lost, we have built an optical structure recognition application based on modern advances in image processing implemented in open source tools, OSRA. OSRA can read documents in over 90 graphical formats including GIF, JPEG, PNG, TIFF, PDF, and PS, automatically recognizes and extracts the graphical information representing chemical structures in such documents, and generates the SMILES or SD representation of the encountered molecular structure images. Until recently most scientific and patent documents dealing with chemistry have described molecular structures either with systematic names or with graphical images of Kekul\'{e} structures. The latter method poses inherent problems in the automated processing that is needed when the number of documents ranges in the hundreds of thousands or even millions since graphical representations cannot be directly interpreted by a computer. To recover this structural information, which is otherwise all but lost, we have built an optical structure recognition application based on modern advances in image processing implemented in open source tools, OSRA. OSRA can read documents in over 90 graphical formats including GIF, JPEG, PNG, TIFF, PDF, and PS, automatically recognizes and extracts the graphical information representing chemical structures in such documents, and generates the SMILES or SD representation of the encountered molecular structure images.}}, added-at = {2019-03-11T21:00:05.000+0100}, author = {Filippov, Igor and Nicklaus, Marc}, biburl = {https://www.bibsonomy.org/bibtex/2ad4bb7d7a460385f5c0de3d5e28290f8/fairybasslet}, booktitle = {Journal of Chemical Information and Modeling}, citeulike-article-id = {4067069}, citeulike-linkout-0 = {http://dx.doi.org/10.1021/ci800067r}, citeulike-linkout-1 = {http://pubs.acs.org/doi/abs/10.1021/ci800067r}, citeulike-linkout-2 = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2889020/}, citeulike-linkout-3 = {http://view.ncbi.nlm.nih.gov/pubmed/19434905}, citeulike-linkout-4 = {http://www.hubmed.org/display.cgi?uids=19434905}, day = 17, doi = {10.1021/ci800067r}, interhash = {5a3a7b00c8ebb55e1119dbaec44e8919}, intrahash = {ad4bb7d7a460385f5c0de3d5e28290f8}, issn = {1549-9596}, journal = {Journal of Chemical Information and Modeling}, keywords = {chemical-information chemical-structures oclcml open-source optical-structure-recognition osra}, month = mar, number = 3, pages = {740--743}, pmcid = {PMC2889020}, pmid = {19434905}, posted-at = {2011-12-20 03:27:21}, priority = {2}, publisher = {American Chemical Society}, timestamp = {2019-03-11T21:06:37.000+0100}, title = {{Optical structure recognition software to recover chemical information: OSRA, an open source solution.}}, url = {http://dx.doi.org/10.1021/ci800067r}, volume = 49, year = 2009 }