| 摘要 |
<P>PROBLEM TO BE SOLVED: To generate tag information for searching the desired image frame of a user automatically and to add the tag information for a plurality of image frames. Ž<P>SOLUTION: Based on the current position and map data detected by a GPS section 14, a moving picture processing device 16 extracts a geographical name near the current position as a perimeter keyword and recognizes the voice by means of a voice recognition unit 15, adds the perimeter keyword as the tag information to an image frame at a time point when the current position is detected if the voice is not recognized, and adds a noun extracted from the recognized voice as the tag information to an image frame at a time point when the voice is detected if the voice is recognized. Ž<P>COPYRIGHT: (C)2010,JPO&INPIT Ž
|
