@conference{285, author = {Burcu Yildiz and Katharina Kaiser and Silvia Miksch}, title = {{pdf2table: A Method to Extract Table Information from PDF files}}, abstract = {Tables are a common structuring element in many documents, such as PDF files. To reuse such tables, appropriate methods need to be develop, which capture the structure and the content information. We have developed several heuristics which together recognize and decompose tables in PDF files and store the extracted data in a structured data format (XML) for easier reuse. Additionally, we implemented a prototype, which gives the user the ability of making adjustments on the extracted data. Our work shows that purely heuristic-based approaches can achieve good results, especially for lucid tables.}, year = {2005}, journal = {2nd Indian International Conference on Artificial Intelligence}, url = {http://ieg.ifs.tuwien.ac.at/pub/yildiz_iicai_2005.pdf}, language = {eng}, }