Micro Focus may provide pre-trained recognizers that you can use with Media Server to recognize objects belonging to generic categories in images and videos.
The following recognizers are currently available, in the package MediaServerPretrainedModels_<VERSION>_COMMON.zip
. When you download this package, ensure that <VERSION>
matches the version of Media Server that you are using.
ObjectClassRecognizer_CommonObjects.dat
Recognizes common objects. This recognizer contains twenty classes across four categories:
ObjectClassRecognizer_HeadAndShoulder.dat
Recognizes people, in order to count them. This recognizer differs from ObjectDetector_Person.dat
because it has been trained to detect only the head and shoulder region, which is useful when you want to count people in a crowded area.
ObjectClassRecognizer_Person.dat
Recognizes people.
ObjectClassRecognizer_RoadScene.dat
Recognizes cars, vans and people.
ObjectClassRecognizer_Gen2_CommonObjects80.dat
Recognizes 80 different types of common object. This is a generation2
recognizer and is expected to provide better accuracy than other types of recognizer, even more specialized recognizers such as ObjectClassRecognizer_Gen3_PersonCar.dat
.
ObjectClassRecognizer_Gen3_CommonObjects20.dat
Recognizes common objects. The classes are the same as for the recognizer ObjectClassRecognizer_CommonObjects.dat
, but this is a generation3
recognizer that provides faster recognition than other types of recognizer.
ObjectClassRecognizer_Gen3_PersonCar.dat
Recognizes people and cars. This is a generation3
recognizer that provides faster recognition than other types of recognizer.
For information about the different types of recognizers, see Recognizer Types. For information about how to import a recognizer into your training database, see Import a Recognizer.
|