| 摘要 |
<P>PROBLEM TO BE SOLVED: To provide a method and device for extracting meta data from a document without the need for including meta data in a box structure or an apparently specified area delimiter. <P>SOLUTION: Described is a method and device for extracting meta data such as a title or a writer from a document image (13) configured of pixels. At least one of images is displayed on a display (12) to a user. A pointing control element of a user such as a mouse or a touch screen is operated by the user, and a selection command is generated. The selection command includes a selection point in the meta data elements of the image. An area configured of foreground pixels is determined. The area includes pixels connected to the selection point. An extraction area (14) is constructed around the area. Finally, the pixels of the extraction area are processed, and the meta data are extracted. <P>COPYRIGHT: (C)2012,JPO&INPIT |
