Train Media Server to Recognize Objects

Before using object class recognition, you must import a recognizer that is provided by Micro Focus. The recognizers provided by Micro Focus are pre-trained, so you do not need to perform any training. For information about the recognizers that are available, see Pre-Trained Object Class Recognizers.

The following diagram shows how Media Server stores information for object class recognition:

The "Media Server database" represents the Media Server datastore file or a database on an external database server. For information on setting up this database, see Set up a Training Database.

The Media Server database can contain any number of recognizers. An object class recognition task uses a single recognizer and finds instances of objects that are described by classes in that recognizer. For example, if you are processing video captured by a CCTV camera, you could use the RoadScene recognizer which contains classes for finding people, cars, and vans.

A recognizer contains a background class and a minimum of one foreground class. The background class contains images of uninteresting (background) objects and this class is never returned in a result. Only foreground classes are returned in results as they represent the categories of objects that you want to recognize.


_FT_HTML5_bannerTitle.htm