Page Summary
-
The Segmentation class is the entry point for identifying foreground and background pixels in an image.
-
To perform segmentation, you first create an InputImage from a source like a Bitmap or ByteBuffer.
-
You then get a Segmenter instance using getClient with appropriate options.
-
The Segmenter processes the InputImage asynchronously and returns a SegmentationMask.
-
Remember to call Segmenter.close() when you are done with the Segmenter instance to release resources.
Entry point for identifying pixels in a supplied image as being part of the foreground or the background.
Segmenter segmenter = Segmentation.getClient(segmenterOptions);
To perform segmentation of an image, you first need to create an instance of InputImage
from a Bitmap
, ByteBuffer
, etc. See InputImage
documentation for more details. For example, the code below creates an InputImage
from a Bitmap
.
InputImage image = InputImage.fromBitmap(bitmap, rotationDegrees);
InputImage
and
asynchronously return a SegmentationMask
. Task<SegmentationMask> task = segmenter.process(image);
task.addOnSuccessListener(...).addOnFailureListener(...);
Public Method Summary
Inherited Method Summary
Public Methods
public static Segmenter getClient ( SelfieSegmenterOptions segmenterOptions)
Gets an instance of Segmenter
that can segment the foreground and the background of an image.
To release the resources associated with a Segmenter
,
you need to ensure that Segmenter.close()
is called on the resulting Segmenter
instance once it will no longer be used.
