摘要 |
A data capture system receives a sequence of document objects and, for each, writes output data values to a structure. A first tier extraction system is adapted to receive each document object. For each required data element, the first tier extraction system obtains identification of a positional element value from a positional data set that includes, as its data element, identification of the required data element; and, if the document object includes a qualifying text string, writes an output data value to the output data structure in association with identification of the required data element. A second tier extraction system receives each such document object that does not include a qualifying text string, performs character recognition on a graphical representation thereof and, for each required data element, writes an output data value to the output data structure in association with identification of the required data element.
|