| 摘要 |
<p><P>PROBLEM TO BE SOLVED: To provide a document image processing apparatus, document image processing method and document image processing program, for automatically extracting an index region from a document image in which indexes are continuously arranged without the time and effort of a user. <P>SOLUTION: The document image processing method includes: a step of determining a small region, which is positioned just before a large region according to a reading order, as a first candidate (S14); a step of evaluating whether or not each first candidate is an index based on a difference from the feature of the large region related for each first candidate (S16); a step of determining a small region, which is positioned just before a first index according to the reading order, as a second candidate (S20); a step of evaluating whether or not each second candidate is the index based on a difference from the feature of the first index related for each second candidate (S24); and a step of extracting small regions, which are determined as the first index and a second index, as index regions (S28). <P>COPYRIGHT: (C)2011,JPO&INPIT</p> |
