![]() |
Face Engine SDK
5.23.1
A face detection, recognition and tracking engine.
|
Descriptor extractor interface. More...
#include <IDescriptor.h>
Public Member Functions | |
| virtual ResultValue< FSDKError, float > | extractFromWarpedImage (const Image &warp, IDescriptor *descriptor) const noexcept=0 |
| Extract descriptor from a warped image. | |
| virtual ResultValue< FSDKError, float > | extractFromWarpedImageBatch (Span< const Image > warps, IDescriptorBatch *descriptorBatch, IDescriptor *aggregation, Span< float > garbageScoreBatch) const noexcept=0 |
| Extract batch of descriptors from a batch of images and perform aggregation. | |
| virtual Result< FSDKError > | extractFromWarpedImageBatch (Span< const Image > warps, IDescriptorBatch *descriptorBatch, Span< float > garbageScoreBatch) const noexcept=0 |
| Extract batch of descriptors from a batch of images. | |
| virtual Result< FSDKError > | validate (Span< const Image > warps, Span< Result< FSDKError >> errors) const noexcept=0 |
| Validate input of multiple frames in a single function call. | |
| virtual uint32_t | getModelVersion () const noexcept=0 |
| Get algorithm model version this extractor works with. | |
| virtual DescriptorType | getDescriptorType () const noexcept=0 |
| Get type of descriptor this extractor works with. | |
| virtual FutureResult | extractFromWarpedImageBatchAsync (Span< const Image > warps, IDescriptorBatch *descriptorBatch, IDescriptor *aggregation, Span< float > garbageScoreBatch) const =0 |
| Asynchronously extract batch of descriptors from a batch of images. | |
Descriptor extractor interface.
Extracts face descriptors from images. The descriptors can be later used for face matching.
| virtual ResultValue<FSDKError, float> fsdk::IDescriptorExtractor::extractFromWarpedImage | ( | const Image & | warp, |
| IDescriptor * | descriptor | ||
| ) | const [pure virtual] |
Extract descriptor from a warped image.
| [in] | warp | image with warped face or human warp. |
| [out] | descriptor | descriptor to fill with data. |
| virtual ResultValue<FSDKError, float> fsdk::IDescriptorExtractor::extractFromWarpedImageBatch | ( | Span< const Image > | warps, |
| IDescriptorBatch * | descriptorBatch, | ||
| IDescriptor * | aggregation, | ||
| Span< float > | garbageScoreBatch | ||
| ) | const [pure virtual] |
Extract batch of descriptors from a batch of images and perform aggregation.
| [in] | warps | span of images with warped faces or human warps. |
| [out] | descriptorBatch | descriptor batch to fill with data. |
| [out] | aggregation | descriptor with aggregation based on descriptor batch. |
| [out] | garbageScoreBatch | span of descriptor scores normalized in range [0, 1] 1 - face on the input warp; 0 - garbage on the input warp. |
| virtual Result<FSDKError> fsdk::IDescriptorExtractor::extractFromWarpedImageBatch | ( | Span< const Image > | warps, |
| IDescriptorBatch * | descriptorBatch, | ||
| Span< float > | garbageScoreBatch | ||
| ) | const [pure virtual] |
Extract batch of descriptors from a batch of images.
| [in] | warps | span of images with warped faces or human warps. |
| [out] | descriptorBatch | descriptor batch to fill with data. |
| [out] | garbageScoreBatch | span of descriptor scores normalized in range [0, 1] 1 - face on the input warp; 0 - garbage on the input warp. DT_HUMAN descriptor does not support garbage score. In a case of DT_HUMAN descriptor, you'll get batch filled by 1.0. |
| virtual FutureResult fsdk::IDescriptorExtractor::extractFromWarpedImageBatchAsync | ( | Span< const Image > | warps, |
| IDescriptorBatch * | descriptorBatch, | ||
| IDescriptor * | aggregation, | ||
| Span< float > | garbageScoreBatch | ||
| ) | const [pure virtual] |
Asynchronously extract batch of descriptors from a batch of images.
| [in] | warps | span of images with warped faces or human warps. |
| [out] | descriptorBatch | descriptor batch to fill with data. |
| [out] | aggregation | descriptor with aggregation based on descriptor batch. |
| [out] | garbageScoreBatch | span of descriptor scores normalized in range [0, 1] 1 - face on the input warp; 0 - garbage on the input warp. DT_HUMAN descriptor does not support garbage score. In a case of DT_HUMAN descriptor, you'll get batch filled by 1.0. |
| virtual DescriptorType fsdk::IDescriptorExtractor::getDescriptorType | ( | ) | const [pure virtual] |
| virtual uint32_t fsdk::IDescriptorExtractor::getModelVersion | ( | ) | const [pure virtual] |
Get algorithm model version this extractor works with.
| virtual Result<FSDKError> fsdk::IDescriptorExtractor::validate | ( | Span< const Image > | warps, |
| Span< Result< FSDKError >> | errors | ||
| ) | const [pure virtual] |
Validate input of multiple frames in a single function call.
| [in] | warps | span of images with warped faces or human warps. |
| [out] | errors | output span of errors for each image. |