Face Engine SDK  5.17.0
A face detection, recognition and tracking engine.
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Macros Groups Pages
fsdk::ILivenessDepthRGBEstimator Struct Referenceabstract

Depth+RGB estimator interface. More...

#include <ILivenessDepthRGBEstimator.h>

Inheritance diagram for fsdk::ILivenessDepthRGBEstimator:
fsdk::IRefCounted

Public Member Functions

virtual Result< FSDKErrorestimate (const Image &depth, const Image &rgb, const Detection &detection, const Landmarks5 &landmarks5, DepthRGBEstimation &out) const noexcept=0
 Checks whether or not the detection corresponds to the real person. More...
 
virtual Result< FSDKErrorestimate (Span< const Image > depths, Span< const Image > rgbs, Span< const Detection > detections, Span< const Landmarks5 > landmarks5, Span< DepthRGBEstimation > outs) const noexcept=0
 Checks several detection on several images to see whether or not the detections corresponds to the real persons. More...
 
virtual Result< FSDKErrorvalidate (Span< const Image > depths, Span< const Image > rgbs, Span< const Detection > detections, Span< const Landmarks5 > landmarks5, Span< Result< FSDKError >> errors) const noexcept=0
 Validates input of multiple frames in a single function call. More...
 
- Public Member Functions inherited from fsdk::IRefCounted
virtual int32_t retain () noexcept=0
 Increase strong reference count. More...
 
virtual int32_t retainLocked () noexcept=0
 Increase strong reference count thread safely. More...
 
virtual int32_t release () noexcept=0
 Decrease strong reference count. More...
 
virtual int32_t getRefCount () const noexcept=0
 Get actual strong reference count. More...
 
virtual int32_t retainWeak () noexcept=0
 Increase weak reference count. More...
 
virtual int32_t releaseWeak () noexcept=0
 Decrease weak reference count. More...
 
virtual int32_t getWeakRefCount () const noexcept=0
 Get actual weak reference count. More...
 

Detailed Description

Depth+RGB estimator interface.

Note
This estimator is designed for face analysis using depth map and RGB frame. It works with 16 bit depth map.
See Also
IDetector for details about how to get a detection of a face.

Member Function Documentation

virtual Result<FSDKError> fsdk::ILivenessDepthRGBEstimator::estimate ( const Image depth,
const Image rgb,
const Detection detection,
const Landmarks5 landmarks5,
DepthRGBEstimation out 
) const
pure virtualnoexcept

Checks whether or not the detection corresponds to the real person.

Parameters
[in]depthsource depth image (depth map),
[in]rgbsource RGB image
[in]detectionface detection on the source RGB image (
See Also
rgb parameter)
Parameters
[in]landmarks5face landmarks on the source RGB image (
See Also
rgb parameter)
Parameters
[out]outDepthRGBEstimation output structure.
Returns
Result with error code.
See Also
DepthRGBEstimation, Image, Detection, Landmarks5, Result and FSDKError for details.
Note
depth image format must be Format::R16,
See Also
Format.
Note
RGB image format must be Format::R8G8B8,
See Also
Format.
virtual Result<FSDKError> fsdk::ILivenessDepthRGBEstimator::estimate ( Span< const Image depths,
Span< const Image rgbs,
Span< const Detection detections,
Span< const Landmarks5 landmarks5,
Span< DepthRGBEstimation outs 
) const
pure virtualnoexcept

Checks several detection on several images to see whether or not the detections corresponds to the real persons.

Parameters
[in]depthssource Depth images span
[in]rgbssource RGB images span
[in]detectionsface detections span on the source RGB images (
See Also
rgbs)
Parameters
[in]landmarks5face landmarks on the source RGB images (
See Also
rgbs parameter)
Parameters
[out]outsDepthRGBEstimation output structures span.
Returns
Result with error code.
See Also
DepthRGBEstimation, Image, Detection, Landmarks5, Span, Result and FSDKError for details.
Note
depth images format must be Format::R16,
See Also
Format.
Note
RGB images format must be Format::R8G8B8,
See Also
Format.
Note
all spans should be based on user owned continuous collections.
all spans should be equal size.
virtual Result<FSDKError> fsdk::ILivenessDepthRGBEstimator::validate ( Span< const Image depths,
Span< const Image rgbs,
Span< const Detection detections,
Span< const Landmarks5 landmarks5,
Span< Result< FSDKError >>  errors 
) const
pure virtualnoexcept

Validates input of multiple frames in a single function call.

Parameters
[in]depthssource Depth images span
[in]rgbssource RGB images span
[in]detectionsface detections span on the source RGB images (
See Also
rgbs)
Parameters
[in]landmarks5face landmarks on the source RGB images (
See Also
rgbs parameter)
Parameters
[out]errorsoutput span of errors for each image.
See Also
DepthRGBEstimation, Image, Detection, Landmarks5, Span, Result and FSDKError for details.
Note
depth images format must be Format::R16,
See Also
Format.
Note
RGB images format must be Format::R8G8B8,
See Also
Format.
Note
all spans should be based on user owned continuous collections.
all spans should be equal size.

The documentation for this struct was generated from the following file: