Package com.libremobileos.yifan.face

Class FaceDetector

java.lang.Object

com.libremobileos.yifan.face.FaceDetector

public class FaceDetector
extends Object

Detect multiple faces in one large Bitmap and returns FaceDetector.Face objects. Requires preprocessed FaceDetector.InputImage objects from FaceDetector.InputImageProcessor.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	FaceDetector.Face	An immutable result returned by a FaceDetector describing what was recognized.
static class	FaceDetector.InputImage	Wrapper around Bitmap to avoid user passing unprocessed data
static class	FaceDetector.InputImageProcessor	Processes Bitmaps to compatible format

Method Summary

Modifier and Type	Method	Description
static FaceDetector	create(Context context, float minConfidence)	Create FaceDetector instance with sensible defaults regarding hardware acceleration (CPU, XNNPACK, 4 threads).
static FaceDetector	create(Context context, float minConfidence, boolean hwAcceleration, boolean enhancedHwAcceleration, int numThreads)	Create FaceDetector instance.
List<FaceDetector.Face>	detectFaces(FaceDetector.InputImage input)	Detect multiple faces in an FaceDetector.InputImage and return their locations.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Method Detail

create

public static FaceDetector create(Context context,
                                  float minConfidence,
                                  boolean hwAcceleration,
                                  boolean enhancedHwAcceleration,
                                  int numThreads)

Create FaceDetector instance.

Parameters:

context - Android Context object, may be in background.

minConfidence - Minimum confidence to track a detection, must be higher than 0.0f and smaller than 1.0f

hwAcceleration - Enable hardware acceleration (NNAPI/GPU)

enhancedHwAcceleration - if hwAcceleration is enabled, use NNAPI instead of GPU. if not, this toggles XNNPACK

numThreads - How many threads to use, if running on CPU or with XNNPACK

Returns:

FaceDetector instance.

See Also:

create(Context, float)

create

public static FaceDetector create(Context context,
                                  float minConfidence)

Create FaceDetector instance with sensible defaults regarding hardware acceleration (CPU, XNNPACK, 4 threads).

Parameters:

context - Android Context object, may be in background.

minConfidence - Minimum confidence to track a detection, must be higher than 0.0f and smaller than 1.0f

Returns:

FaceDetector instance.

See Also:

create(Context, float, boolean, boolean, int)

detectFaces

public List<FaceDetector.Face> detectFaces(FaceDetector.InputImage input)

Detect multiple faces in an FaceDetector.InputImage and return their locations.

Parameters:

input - Image, processed with FaceDetector.InputImageProcessor

Returns:

List of FaceDetector.Face objects