Benchmark results

Facial recognition

Facial recognition accuracy (NIST Standards)

The table below shows Face SDK quality metrics based on the National Institute of Standards and Technology (NIST) Standards:

NIST Face Recognition Vendor Test (FRVT) 1:1	Score
VISA* True Acceptance Rate (@FAR 1E-6)	99.70%
Mugshot* True Acceptance Rate (@FAR 1E-5)	99.76%
Border* True Acceptance Rate (@FAR: 1E-6)	99.75%

Click here to see the description of image types from the table*

• VISA – Full Frontal image type. The images have a size of 252x300 pixels. The mean interocular distance (IOD) is 69 pixels.
• Mugshot – Full Frontal image type. The images are of variable sizes. The mean IOD is 113 pixels.
• Border – The images are taken with a camera, which is oriented by an attendant toward a cooperating subject. This is done under time constraints so there are role, pitch and yaw angle variations. Background illumination is sometimes strong, so the face is under-exposed. There is some perspective distortion due to close range images. Some faces are partially cropped.

Facial recognition accuracy on extended LFW dataset with Wild images

For this test we used extended LFW dataset (LFW dataset + our internal dataset). The set of mismatched pairs was increased and LFW errors were fixed to get accurate measurements at low FAR.

ROC-curve

FAR	9.300 TAR (%)	12.30 TAR (%)	12.50 TAR (%)	12.100 TAR (%)	12.1000 TAR (%)
1e-4	98.7	98.9	99.2	99.4	99.5
1e-5	98.0	98.1	98.7	99.1	99.4
1e-6	96.6	96.7	97.9	98.5	99.3
1e-7	93.2	94.3	96.3	97.5	98.9
1e-8	32.2	88.0	89.5	94.1	97.7
1e-9	10.5	82.0	80.9	84.9	93.9

Recognition errors for the most relevant methods (12vX)

12v30

12v50

12v100

12v1000

Template extraction speed using CPU and GPU

Desktop

Method	GPU (NVIDIA GTX 1070)	CPU (Core i5-9400 4.0GHz)
12v1000	47 ms	442 ms
9v300	10 ms	292 ms
12v100	8 ms	49 ms
12v50	6 ms	21 ms
12v30	5 ms	12 ms

Mobile

Method	CPU (Qualcomm Snapdragon 845)
12v1000	7968ms
9v300	1960ms
12v100	801ms
12v50	270ms
12v30	150ms

Note: The speed test was performed using Google Pixel 3.

Facial recognition speed for CPU

Intel Xeon E5-2683 v4 GHz*

Recognition method	Template generation (ms)	Accelerated Matching 1:N (ms)			Matching 1:1 (ms)
		N = 104	N = 106	N = 107
6.7	40 (45**)	0,25	12,1	126	0,04
7.7	170 (180**)	0,25	12,1	126	0,04
8.7	20 (20**)	0,25	12,1	126	0,04
9.30	55	0,18	12,0	117	0,04
9.300	402	0,18	12,0	117	0,04
9.1000	1092	0,18	12,0	117	0,04
9.30mask	38	0,18	12,0	117	0,04
9.300mask	263	0,18	12,0	117	0,04
9.1000mask	469	0,18	12,0	117	0,04
10.30	44	0,18	12,0	117	0,04
10.100	71	0,18	12,0	117	0,04
10.1000	1061	0,18	12,0	117	0,04
11.1000	1396	0,22	15,0	151	0,04
12.30	23***	0,20	15,0	120	0,04
12.50	37***	0,20	15,0	120	0,04
12.100	79***	0,20	15,0	120	0.04
12.1000	647***	0,40	20,0	170	0,04

CPU Core i7 4.5 GHz*

Recognition method	Template generation (ms)	Accelerated Matching 1:N (ms)			Matching 1:1 (ms)
		N = 104	N = 106	N = 107
6.7	40 (45**)	0,25	12,1	126	0,04
7.7	170 (180**)	0,25	12,1	126	0,04
8.7	20 (20**)	0,25	12,1	126	0,04
9.30	30	0,18	12,0	117	0,04
9.300	260 (125***)	0,18	12,0	117	0,04
9.1000	730 (305***)	0,18	12,0	117	0,04
9.30mask	20	0,18	12,0	117	0,04
9.300mask	160 (79***)	0,18	12,0	117	0,04
9.1000mask	290 (144***)	0,18	12,0	117	0,04
10.30	24 (16***)	0,18	12,0	117	0,04
10.100	40 (24***)	0,18	12,0	117	0,04
10.1000	690 (355***)	0,18	12,0	117	0,04
11.1000	865 (425***)	0,22	15,0	151	0,04
12.30	10***	0,20	15,0	120	0,04
12.50	18***	0,20	15,0	120	0,04
12.100	41***	0,20	15,0	120	0.04
12.1000	412***	0,40	20,0	170	0,04

* – characteristics specified in this table are given for a single-core CPU.
** – template extraction time when processing_less_memory_consumption was set to true in the FacerecService.createRecognizer call for creating a Recognizer.
*** – template extraction time using the AVX2 instruction set (see Facial Recognition).

Note:

• Accelerated search time is given for k=1. As for larger values of k, the time will increase up to the search time without acceleration.
• Accelerated search is implemented only for the recognition methods 6.5, 6.6, 6.7, 7.3, 7.6, 7.7, 8.6, 8.7, 9.30, 9.300, 9.1000, 10v30, 10v100, 10v1000, 11v1000, 12.30, 12.50 , 12.100, 12.1000.
• To achieve this speed, the templates in the index must be located in order of creation (by using the Recognizer.processing or Recognizer.loadTemplate method).
• To achieve higher speed, use GPU (see GPU Usage).

Memory characteristics

Recognition method	Serialized template size (Bytes)	Template size in RAM (Bytes)	Memory consumption* (MB)
6.7	536	636	105 (85**)
7.7	536	636	195 (163**)
8.7	536	636	52 (40**)
9.30	280	380	155
9.300	280	380	210
9.1000	280	380	290
10.30	280	380	160
10.100	280	380	180
10.1000	280	380	270
11.1000	296	396	480
12.30	230	330	160
12.50	261	361	170
12.100	337	437	180
12.1000	400	500	440

* – the amount of memory consumed doesn't depend on the number of the Recognizer objects created by this method
** – memory consumption when processing_less_memory_consumption was set to true in the FacerecService.createRecognizer call for Recognizer creation

Face detection

Face detection speed

CPU Intel Xeon E5-2683 v4 (Single-Core)

Configuration file	Capture time (ms)
	640x480, 1 face	640x480, 4 faces	1280x720, 1 face	1280x720, 4 faces	1920x1080, 1 face	1920x1080, 4 faces
common_capturer_blf_fda_auto.xml	9-43	17-52	17-50	17-55	33-69	25-57
common_capturer_blf_fda_back.xml	43	52	50	55	67	57
common_capturer_blf_fda_front.xml	9	17	17	17	33	25
common_capturer_refa_fda_a.xml	1001	996	777	792	864	858
common_capturer_uld_fda.xml (min_size=150)	19	28	24	29	36	30
common_capturer_uld_fda.xml (min_size=90)	88	97	93	100	109	102
common_capturer_uld_fda.xml (min_size=50)	377	385	375	385	402	397
safety_city_q1.xml	99	107	100	112	110	117
safety_city_q2.xml	376	383	379	385	399	393
remote_identification_q1.xml	1000	1001	773	791	863	858
remote_identification_q2.xml	44	51	50	55	66	56
access_control_system_one_face_q1.xml	44	52	50	56	66	56
access_control_system_one_face_q2.xml	43	52	50	55	67	55
access_control_system_one_face_q3.xml	88	96	94	98	107	102
access_control_system_several_faces_q1.xml	1004	1007	773	788	863	858
access_control_system_several_faces_q2.xml	87	95	92	98	106	101
common_capturer4_fda.xml	23	35	49	108	94	143
common_capturer4_fda_with_angles.xml	481	697	414	768	312	410
common_capturer4_mesh.xml	27	60	57	142	102	175
common_capturer4_mesh_with_angles.xml	492	732	424	788	321	443
common_capturer4_fda_singleface.xml	31	-	60	-	112	-
common_capturer4_mesh_singleface.xml	34	-	68	-	120	-

GPU (NVIDIA GTX 1080 Ti)

Configuration file	Capture time (ms)
	640x480, 1 face	640x480, 4 faces	1280x720, 1 face	1280x720, 4 faces	1920x1080, 1 face	1920x1080, 4 faces
common_capturer_blf_fda_auto.xml	4-5	10-12	6-8	13-14	17-20	24-27
common_capturer_blf_fda_back.xml	5	12	8	14	20	27
common_capturer_blf_fda_front.xml	4	10	6	13	17	24
common_capturer_refa_fda_a.xml	236	240	229	235	170	176
common_capturer_uld_fda.xml (min_size=150)	4	10	5	11	13	20
common_capturer_uld_fda.xml (min_size=90)	14	21	17	23	26	34
common_capturer_uld_fda.xml (min_size=50)	27	34	27	35	47	49

CPU Core i7 4.5 GHz (Single-Core)

Configuration file	Capture time (ms)
	640x480, 1 face	640x480, 4 faces	1280x720, 1 face	1280x720, 4 faces	1920x1080, 1 face	1920x1080, 4 faces
common_capturer4_fda.xml	13	25	34	49	81	103
common_capturer4_fda_with_angles.xml	282	387	260	356	273	370
common_capturer4_mesh.xml	18	47	39	72	87	735
common_capturer4_mesh_with_angles.xml	291	415	268	383	281	398
common_capturer_blf_fda_auto.xml	6-30	12-36	8-32	14-38	19-44	26-51
common_capturer_blf_fda_back.xml	30	36	32	38	44	51
common_capturer_blf_fda_front.xml	6	12	8	14	19	26
common_capturer_refa_fda_a.xml	644	650	512	518	580	586
common_capturer_uld_fda.xml (min_size=150)	12	18	13	19	21	28
common_capturer_uld_fda.xml (min_size=90)	58	70	60	73	77	91
common_capturer_uld_fda.xml (min_size=50)	253	272	253	273	281	302
common_capturer4_fda_singleface.xml	16	-	51	-	123	-
common_capturer4_mesh_singleface.xml	23	-	58	-	129	-

Note: Actual capture time may vary depending on the image content.

Capturer configuration files

Click here to see the list of the capturer configuration files

File	Detector	Set of points	Angles (roll/yaw/pitch)	Description and use case
common_capturer4_fda.xml	lbf	fda	[-30;30][-60;60][-60;60]	Frontal face detector.
common_capturer4_fda_with_angles.xml	lbf	fda	[-90;90][-60;60][-60;60]	Frontal face detector. Adapted for a wide range of head rotation angles.
common_capturer4_fda_with_angles_noise.xml	lbf	fda	[-90;90][-60;60][-60;60]	Frontal face detector. Adapted for a wide range of head rotation angles. Suitable for images with high noise level.
common_capturer4_fda_singleface.xml	lbf	fda	[-30;30][-60;60][-60;60]	Only one frontal face is detected.
common_capturer4_fda_singleface_with_angles.xml	lbf	fda	[-90;90][-75;75][-60;60]	Only one frontal face is detected. The detector is adapted for a wide range of head rotation angles.
common_capturer4_fda_singleface_with_angles_noise.xml	lbf	fda	[-90;90][-75;75][-60;60]	Only one frontal face is detected. The detector is adapted for a wide range of head rotation angles. Suitable for images with high noise level.
common_capturer4_lbf.xml	lbf	doublelbf	[-30;30][-60;60][-60;60]	Frontal face detector.
common_capturer4_lbf_singleface.xml	lbf	doublelbf	[-30;30][-60;60][-60;60]	Only one frontal face is detected.
common_capturer4_mesh.xml	lbf	mesh	[-30;30][-60;60][-60;60]	Frontal face detector that allows you to get a 3D face mask.
common_capturer4_mesh_with_angles.xml	lbf	mesh	[-90;90][-60;60][-60;60]	Frontal face detector adapted for a wide range of head rotation angles that allows you to get a 3D face mask.
common_capturer4_mesh_with_angles_noise.xml	lbf	mesh	[-90;90][-60;60][-60;60]	Frontal face detector adapted for a wide range of head rotation angles and suitable for images with high noise level. The detector allows you to get a 3D face mask.
common_capturer4_mesh_singleface.xml	lbf	mesh	[-30;30][-60;60][-60;60]	Only one frontal face is detected. The detector allows you to get a 3D face mask.
common_capturer4_mesh_singleface_with_angles.xml	lbf	mesh	[-90;90][-75;75][-60;60]	Only one frontal face is detected. The detector is adapted for a wide range of head rotation angles and allows you to get a 3D face mask.
common_capturer4_mesh_singleface_with_angles_noise.xml	lbf	mesh	[-90;90][-75;75][-60;60]	Only one frontal face is detected. The detector is adapted for a wide range of head rotation angles, suitable for images with high noise level and allows you to get a 3D face mask.
common_capturer_blf_fda_front.xml	blf	fda	[-70;70][-90;90][-70;70]	Detection of large face images (the face should take up most of the frame size). Suitable for detection of masked faces.
common_capturer_blf_fda_back.xml	blf	fda	[-70;70][-90;90][-70;70]	Detection of several faces or small face images. Suitable for detection of masked faces.
common_capturer_blf_fda_auto.xml	blf	fda	[-70;70][-90;90][-70;70]	Detection of large and small face images (the parameters `resolution_width` and `min_face_size` should be specified in the configuration file). Suitable for detection of masked faces.
common_capturer_refa_fda_a.xml	refa	fda	[-70;70][-90;90][-70;70]	Face detector recommended for use in expert systems. The detector provides face detection with the largest coverage of rotation angles and maximum quality (including masked faces).
common_capturer_uld_fda.xml.xml	uld	fda	[-70;70][-90;90][-70;70]	Detection of large and small face images. Suitable for detection of masked faces.
common_video_capturer_fda.xml	lbf	fda	[-30;30][-60;60][-60;60]	Frontal face video tracker (RGB only).
common_video_capturer_lbf.xml	lbf	singlelbf	[-30;30][-60;60][-60;60]	Frontal face video tracker (RGB only).
common_video_capturer_mesh.xml	lbf	mesh	[-30;30][-60;60][-60;60]	Frontal face video tracker (RGB only) that allows you to get a 3D face mask.
fda_tracker_capturer.xml	lbf	fda	[-30;30][-60;60][-60;60]	Frontal face video tracker.
fda_tracker_capturer.w.xml	lbf	fda	[-30;30][-60;60][-60;60]	Frontal face video tracker that can be used in case of insufficient lighting. Note that false detections can occur a bit more often in this case.
fda_tracker_capturer_mesh.xml	lbf	fda	[-30;30][-60;60][-60;60]	Frontal face video tracker that allows you to get a 3D face mask.
fda_tracker_capturer_fake_detector.xml	lbf	fda	[-30;30][-60;60][-60;60]	Detection speed is higher because only fitter is used (no detector). Suitable only if a face takes up most of the image size.
fda_tracker_capturer_blf.xml	blf	fda	[-30;30][-60;60][-60;60]	Frontal face video tracker. Suitable for detection of masked faces.
fda_tracker_capturer_refa_a.xml	refa	fda	[-70;70][-90;90][-70;70]	Frontal face video tracker. Recommended for use in expert systems. The tracker provides face detection with the largest coverage of rotation angles and maximum quality (including masked faces).
fda_tracker_capturer_uld_fda.xml.xml	uld	fda	[-70;70][-90;90][-70;70]	Frontal face video tracker that can be used to detect faces of different size. Suitable for detection of masked faces.
manual_capturer_fda.xml	lbf	fda	[-30;30][-60;60][-60;60]	Eye points should be manually specified. The remaining points are calculated based on the eye points.
manual_capturer_mesh.xml	lbf	mesh	[-30;30][-60;60][-60;60]	Eye points should be manually specified. The remaining points are calculated based on the eye points that allows you to get a 3D face mask.
video_worker_fdatracker_refa_fda.xml	refa	fda	[-70;70][-90;90][-70;70]	Face detector recommended for use in expert systems. The detector provides face detection with the largest coverage of rotation angles and maximum quality (including masked faces).

Processing Blocks

Face detection speed

CPU Intel Xeon E5-2683 v4 (Single-Core)

Modification	Version	Default parameters	Detection time (ms)
			640x480	1280x720	1920x1080
uld	1	precision_level=1, confidence_threshold=0.7, coarse_confidence_threshold=0.3	7	8	9
		precision_level=2, confidence_threshold=0.7, coarse_confidence_threshold=0.3	37	40	43
		precision_level=3, confidence_threshold=0.7, coarse_confidence_threshold=0.3	193	192	203
ssyv	1	confidence_threshold=0.5, iou_threshold=0.5	153	153	157
	2		47	49	54
	3		96	99	104
	4		1355	1419	1420
blf_front	1	confidence_threshold=0.67, iou_threshold=0.5	4	6	11
blf_back	1		12	14	20

Body and object detection speed

CPU Intel Xeon E5-2683 v4 (single-core)

Type	Modification	Version	Detection time (ms)
			640x480	1280x720	1920x1080
HUMAN_BODY_DETECTOR	ssyv	1	238	241	244
OBJECT_DETECTOR	ssyx	1	2027	2023	2028

Face estimation performance

The speed test was performed using CPU Intel Xeon E5-2683 v4 (single-core)

AGE_ESTIMATOR

Modification	Version	Detection time (ms)	Accuracy, (average error in years)
light	1	2	5.5
	2	2	4.9
heavy	1	6	4.7
	2	6	3.5

GENDER_ESTIMATOR

Modification	Version	Detection time (ms)	Accuracy, %
light	1	2	95
	2	2	96
heavy	1	6	96
	2	6	97
	3	6	97.5

EMOTION_ESTIMATOR

Modification	Version	Detection time (ms)	Accuracy, %
heavy	1	29	80

MASK_ESTIMATOR

Modification	Version	Detection time (ms)
light	1	2
	2	2

Liveness Estimator performance

CPU Intel Xeon E5-2683 v4 (single core)

Modification	Version	Detection time (ms)	APCER[BPCER=0.05]
2d_additional_check	1	41	0.37
2d	1	694	0.35
	2	250	0.1
2d_light	1	6	0.14
	2	18	0.09

modification=2d, version=1

modification=2d, version=2

modification=2d_light, version=1

modification=2d_light, version=2

Quality Assessment Estimator performance

CPU Intel Xeon E5-2683 v4 (single-core)

Modification	Detection time (ms)	The worst samples by total_score, discarded, (%)	FNMR	FPR
assessment	65	1	0.0097	1.98E-07
		5	0.0087	2.00E-07
		10	0.0081	2.11E-07
estimation	97	1	0.0079	1.93E-07
		5	0.0062	1.93E-07
		10	0.0059	1.97E-07

Face Fitter speed

CPU Intel Xeon E5-2683 v4 (single-core)

Modification	Version	Detection time (ms)
tddfa_faster	1	3
tddfa	1	7
mesh	1	7

Human Pose Estimator speed

CPU Intel Xeon E5-2683 v4 (single-core)

Modification	Version	Detection time (ms)
heavy	1	195

Estimation of facial attributes

Facial attributes	Accuracy
Gender	95%
Emotion	80%
Age	3.95 y/o (mean Average Error)
No mask (face without a mask)	99%
Has mask (face with a mask)	97%