BOPI (Official Bulletin on Industrial Property), Spain 1886-1997
We ran a new advanced OCR system throuhgout the entire BOPI collection from 1886 to 1997, page by page. After getting the text, we automatically indexed all the words in a PostgreSQL database. The result is a quick system to find any word or phrase within the collection in milliseconds. Then you get the recognized text and the original image in a PDF file.
We hope you enjoy it. If you do so, please quote our articles and books. Add a note in your papers as follows: Francisco Llorens and Patricio Sáiz: Advance Search Engine for the Spanish Official Bulletin on Industrial Property, OEPM-UAM, Madrid, 2014 and this link: http://spain.iprgazettes.org/