| 摘要 |
The method of processing postal objects of large size in order to read automatically a postal address (AD) on each object consists in acquiring a digital image of each object at a certain level of resolution; in detecting in the image one or more zones of interest (ZI) apparently containing a postal address; in performing automatic address recognition on each zone of interest in order to extract a postal address (AD) of the object, and in the event of the automatic address recogition failing, in displaying each zone of interest (ZI) on a screen so that a video-coding operator can read the postal address (AD) of the object. Each zone of interest (ZI) is displayed on the screen on a screen context background (F) that is representative of the object but at a level of resolution that is lower than the level of resolution of the digital image and the zone of interest. In this way, the video-coding operator has an overall view of the detected zones of interest, thus making it easier to read the postal address of the object.
|
