CLiDE Pro: The Latest Generation of CLiDE, a Tool for Optical Chemical Structure Recognition Export

@article{ValkoJ09, abstract = {We present CLiDE Pro, the latest version of the output of the long-term CLiDE project for the development of tools for automatic extraction of chemical information from the literature. CLiDE Pro is concerned with the extraction of chemical structure and generic structure information from electronic images of chemical molecules available online as well as pages of scanned chemical documents. The information is extracted in three phases, first the image is segmented into text and graphical regions, then graphical regions are analyzed and where possible the connection tables are reconstructed, and finally any generic structures are interpreted by matching R-groups found in structure diagrams with the ones located in the text. The program has been tested on a large set of images of chemical structures originating from various sources. The results demonstrate good performance in the reconstruction of connection tables with few errors in the interpretation of the individual drawing features found in the structure diagrams. This full test set is presented for use in the validation of other similar systems.}, author = {Valko, Aniko T. and Johnson, A. Peter}, citeulike-article-id = {4281157}, citeulike-linkout-0 = {http://dx.doi.org/10.1021/ci800449t}, citeulike-linkout-1 = {http://pubs.acs.org/doi/abs/10.1021/ci800449t}, day = {27}, doi = {10.1021/ci800449t}, journal = {Journal of Chemical Information and Modeling}, keywords = {binary, bonds, clide, components, connected, contour, correction, crossing, csr, curved, fraction, generic, kruskal, ocr, segmentation, structure, superatom}, month = {April}, number = {4}, pages = {780--787}, posted-at = {2009-04-07 08:29:48}, priority = {2}, title = {CLiDE Pro: The Latest Generation of CLiDE, a Tool for Optical Chemical Structure Recognition}, url = {http://dx.doi.org/10.1021/ci800449t}, volume = {49}, year = {2009} }

TY - JOUR ID - ValkoJ09 L3 - citeulike-article-id:4281157 N2 - We present CLiDE Pro, the latest version of the output of the long-term CLiDE project for the development of tools for automatic extraction of chemical information from the literature. CLiDE Pro is concerned with the extraction of chemical structure and generic structure information from electronic images of chemical molecules available online as well as pages of scanned chemical documents. The information is extracted in three phases, first the image is segmented into text and graphical regions, then graphical regions are analyzed and where possible the connection tables are reconstructed, and finally any generic structures are interpreted by matching R-groups found in structure diagrams with the ones located in the text. The program has been tested on a large set of images of chemical structures originating from various sources. The results demonstrate good performance in the reconstruction of connection tables with few errors in the interpretation of the individual drawing features found in the structure diagrams. This full test set is presented for use in the validation of other similar systems. IS - 4 JF - Journal of Chemical Information and Modeling EP - 787 TI - CLiDE Pro: The Latest Generation of CLiDE, a Tool for Optical Chemical Structure Recognition VL - 49 SP - 780 KW - binary KW - bonds KW - clide KW - components KW - connected KW - contour KW - correction KW - crossing KW - csr KW - curved KW - fraction KW - generic KW - kruskal KW - ocr KW - segmentation KW - structure KW - superatom AU - Valko, Aniko AU - Johnson, Peter PY - 2009/04/27/ UR - http://dx.doi.org/10.1021/ci800449t ER -