Glossary#

Term	Definition
Bestshot	The frame of the video stream in which the face is captured in the best angle for further use in a face recognition system
Bbox	A rectangle that bounds the image space with a detected face
Intersection Over Union (IOU)	Parameter determines the coefficient of intersection of two detections
JSON	A text-based data exchange format based on JavaScript
Liveness	Software method that enables you to confirm whether a person in one or more images is "real" or a fraudster using a fake ID (printed face photo, video, paper or 3D mask)
MessagePack (MsgPack)	A fast and compact binary serialization format for data exchange, a more efficient alternative to JSON
Attributes	Gender and age of a person determined automatically by the system
Detection	Actions to find areas of the image containing faces
Spoofing attack	Substitution of a real person for a fake image (for example, a photograph) to deceive the system

Introduction#

This document contains information about VisionLabs LUNA KIOSK and describes how the components work.

VisionLabs LUNA KIOSK (hereinafter referred to as System) is a set of libraries that provide the possibility of realizing real-time operation to perform face detection in a frame, check the vitality of a person and transfer data to an external system.

The System is designed for:

receiving and processing a color video stream from a video recording device,
checking the image quality,
selecting the bestshot,
face detection by machine calculation method on two images,
checking the presented image by Liveness-algorithms,
protection against image spoofing by depth map analysis,
subsequent transfer of the bestshot to device integration systems.

System requirements#

The minimum system requirements below (Table 1 and Table 2) must be met in order to install the full System package.

Table 1. Minimum system requirements for x64 architecture

Required Resource	Recommended
Processor	Intel(R) Core(TM) i3-10110U
RAM	4GB or more
Hard disk drive	HDD or SSD at least 1,4 B
Operating system	Windows 10 (64 bit); Ubuntu 24.04 x64; Debian 10 x64
Instruction Support	Advanced Vector Extensions 2 (AVX2)

To run the application on Windows, install the Visual C++ Redistributable package.

Table 2. Minimum system requirements for ARM architecture

Required Resource	Recommended
Processor	Rockchip RK3588S
RAM	4GB or more
Hard disk drive	HDD or SSD at least 128GB
Operating system	Armbian 23 (aarch64)

Correct operation of the System is ensured by Intel® RealSense™ Camera D400-Series 3D cameras with firmware version 5.15.0.2, VLS LUNA CAMERA 3D cameras and VLS LUNA CAMERA 2D IR cameras:

Intel® RealSense™ Depth Cameras D415;
Intel® RealSense™ Depth Cameras D435;
Intel® RealSense™ Depth Cameras D435i;
VLS LUNA CAMERA 3D / VLS LUNA CAMERA 3D Embedded;
VLS LUNA CAMERA 2D.

For information about VLS LUNA CAMERA 3D / VLS LUNA CAMERA 3D Embedded, please contact your VisionLabs representative.

Use USB 3.0 to work with Intel® RealSense™ Camera D400-Series 3D cameras, VLS LUNA CAMERA 3D and VLS LUNA CAMERA 2D.

System architecture#

A high-level diagram of the System architecture is shown below (Figure 1).

The system consists of the following components:

RSEngine is a component that includes:
VisionLabs SDK library from the VisionLabs development kit for image processing;
libraries:
- RealSense2 SDK–for work with Intel RealSense camera;
- VLS LUNA CAMERA 3D SDK–for work with VLS LUNA CAMERA 3D camera;
- VLS LUNA CAMERA 2D SDK–for work with VLS LUNA CAMERA 2D camera;
Camera monitoring, designed to check the status of the camera;
RSE Server–WebSocket server for interaction with external system WebSocket Client.

Algorithm#

Bestshot selection#

The interaction of components when selecting the bestshot is shown below (Figure 2).

Interaction diagram of System components when selecting the bestshot

An explanation for the figure is presented below (Table 3).

Table 3. The description of the interaction diagram of the System components when selecting the bestshot

Step	Description
(1)	The RSE Server receives a WebSocket connection request from a client. Example request: `GET ws://127.0.0.1:4444/`–establishing a WebSocket connection. `0`–content of the message to start the session
(2)	RSE Server sends a request to RSEngine to launch the camera (to the camera library). Depending on which camera is connected, `IntelRealSense`, `VLS LUNA CAMERA 3D` or `VLS LUNA CAMERA 2D`, RSE Server passes the request to the appropriate RSEngine library: `RealSense2 SDK`, `VLS LUNA CAMERA 3D SDK`, `VLS LUNA CAMERA 2D SDK`.
(3)	Camera library launches the camera
(4)	The camera library receives RGB, IR, Depth video streams from the camera, splits them into frames and analyzes
(5)	The camera library passes a set of frames to the RSE Server. Depending on the `cs_communication` parameter, different data is transferred: `- cs_communication = msg-pack`: all three frames (RGB, IR, Depth) is transferred `- cs_communication = json`: only RGB frame is transferred
(6)	RSE Server sends a request to frame processing (performed on each frame) to the VisionLabs SDK
(7)	SDK VisionLabs performs: selection of every third frame from the incoming video stream (the number of frames is not adjustable in the settings); face detection on each frame; determination of attributes and parameters of detected faces; checking threshold values of the received parameters (head position, image quality, etc.). If all checks are passed, the process continues (go to step 8). If at least one check fails, SDK VisionLabs sends a request to the camera for new frames to perform a second check as long as there is detection (return to step 4)
(8)	VisionLabs SDK performs a Liveness check and compares the resulting value of the Liveness score to the threshold one. If the received Liveness value is higher than the threshold, then the current frame becomes the bestshot. If the received Liveness value is below the threshold, SDK VisionLabs sends a request to the camera to to receive new frames to perform a second check as long as there is detection (return to step 4)
(9)	If the Liveness check is successful, the received bestshot and facial attributes are sent to the RSE Server
(10)	RSE Server converts the selected bestshot and meta-information into MessagePack and sends it to the client in an external system

Monitor camera status#

The interaction of components when monitoring the state of the camera is shown below (Figure 3).

Diagram of component interaction when monitoring camera status

An explanation for the figure is presented below (Table 4).

Monitoring is started by default once every 300 seconds, you can change the duration in the camera-monitoring and camera-monitoring-delay parameters in the rsengine.conf file.

Table 4. The description of the interaction diagram of the System components when monitoring the camera state

Step	Description
(1)	RSE Server sends a request to RSEngine to launch monitoring the camera
(2)	Camera Monitoring sends a request to the camera library for camera status—RealSense2 SDK, VLS LUNA CAMERA 3D SDK or VLS LUNA CAMERA 2D SDK depending on which camera is connected IntelRealSense, VLS LUNA CAMERA 3D or VLS LUNA CAMERA 2D SDK
(3)	The camera library transfers a request for camera status
(4)	The camera library receives the camera status
(5)	The camera library passes the camera status to the camera monitoring
(6)	RSEngine transfers camera status information to RSE Server
(7)	RSE Server entries camera status data to the registry (on Windows) or to the ./logs working folder (on Ubuntu 24.04 x64, Debian 10 x64 and Armbian 23)

Component description#

RSEngine component#

RSEngine provides the interaction of the following libraries within the system:

VisionLabs LUNA SDK
RealSense2 SDK
VLS LUNA CAMERA 3D SDK
VLS LUNA CAMERA 2D SDK

This integration ensures efficient and reliable communication between these libraries, enabling advanced functionalities for image and video processing.

VisionLabs LUNA SDK component#

VisionLabs LUNA SDK is a comprehensive software development kit that includes specialized libraries and neural networks designed for advanced image analysis. Its key capabilities include:

Face detection: Identifying faces in images and locating key facial landmarks.
Best shot selection: Automatically selecting the highest-quality frame from a video stream for further processing.
Image attribute estimation: Analyzing image attributes for further Liveness estimations.
Liveness estimation: Evaluating faces in images using Liveness algorithms to prevent spoofing attacks.

Note: All estimations described below are performed to ensure that the image meets Liveness requirements. These estimations are internal. Results are only displayed in cases of errors, such as when an image or face attribute is unsuitable for Liveness estimation. For more details on error codes and their descriptions, see Appendix 2: Status Codes and Error Descriptions.

All estimations described below are performed to ensure that the image meets Liveness requirements. These estimations are internal. and the results are not transmitted externally. The result of the check can only be shown in case of an error, if any attribute of the image/face is not suitable for the Liveness estimation (see the description of errors in “Appendix 2. Status codes and error descriptions”);

RealSense2 SDK component#

RealSense2 SDK is a component that provides the following functionalities:

Image acquisition: Receives incoming images from Intel RealSense cameras.
Parameter configuration: Allows you to configure detection parameters to suit specific requirements.
Camera control: Enables turning the camera on or off and adjusting various settings, such as:
Laser backlight brightness
Auto exposure
Brightness levels
Automatic connection management:
Automatically updates the connection with the camera.
If the connection is lost, the system attempts to reconnect to the camera.
In case reconnection fails, a soft reset of the connection cable is performed.
If all recovery operations are unsuccessful, the issue will be logged in the camera status report within the system logs.

Component: VLS LUNA CAMERA 3D SDK#

VLS LUNA CAMERA 3D SDK is a component that provides the following functionalities:

Image acquisition: Receives incoming images from VLS LUNA CAMERA 3D or VLS LUNA CAMERA 3D Embedded devices.
Parameter configuration: Allows you to configure detection parameters to meet specific requirements.
Camera control: Provides the ability to turn the camera on or off and adjust various settings, such as:
Laser illumination brightness
Auto exposure
Brightness levels

Component VLS LUNA CAMERA 2D SDK#

VLS LUNA CAMERA 2D SDK is a component that provides the following functionalities:

Image acquisition: Receives incoming images from VLS LUNA CAMERA 2D infrared cameras.
Parameter configuration: Allows you to configure detection parameters to meet specific requirements.
Camera control: Provides the ability to turn the camera on or off as needed.
Frame rotation adjustment: Enables changing the rotation angle of the camera's video frame.

Camera functions#

Face detection#

The detector employs advanced face detection algorithms to address the following tasks:

Face detection: Identifying faces within an image.
Key point localization: Locating five key facial landmarks: two for the eyes, one for the tip of the nose, and two for the corners of the mouth.
Detection quality estimation: Evaluating the probability that the detected object is indeed a face, ensuring high accuracy and reliability.

Image quality estimation#

The quality of an image is evaluated based on the following parameters:

Blurriness
Lightness or overexposure
Darkness or Underexposure

Mouth estimation#

The mouth estimation evaluates the following parameters:

Open: Indicates whether the mouth is open.
Occluded: Detects if the mouth is blocked or covered by an external object.
Smiling: Identifies the presence of a smile.

Eye state estimation#

The eye state estimation evaluates the following parameters:

Closed: Eyes are shut.
Open: Eyes are open.
Occluded: Eyes are covered, for example, by sunglasses or other objects.

Head pose estimation#

The head pose estimation determines a person's head rotation angles in 3D space, specifically along the pitch, yaw, and roll axes:

Pitch: This angle measures the vertical tilt of the head. It limits the head rotation along the X-axis.
Yaw: This angle measures the horizontal rotation of the head. It limits the head rotation along the Y-axis.
Roll: This angle measures the lateral tilt of the head. It limits the head rotation along the Z-axis.

Depth Liveness estimation#

The "vitality" of a person in the image is verified using a depth map.

The process involves analyzing a 16-bit depth matrix. It contains detailed information about the distances of scene objects (such as faces) relative to the camera's viewpoint. This analysis helps determine whether the subject is a live person or a spoof, such as a photograph or mask.

IR Liveness estimation#

The "vitality" of a person in the image is verified through infrared (IR) image analysis. This process ensures that the subject is a live human and not a spoof, such as a printed photo or mask.

Note: The camera must be equipped with infrared illumination to perform this check effectively.

LivenessOneShotRGB estimation#

The LivenessOneShotRGB estimation determines whether a person's face is real or fake by detecting and mitigating various types of spoofing attacks. These include:

Printed photo attack: One or more printed photos of another person are used.
Video replay attack: A pre-recorded video of another person is displayed to trick the camera.
Printed mask attack: An imposter cuts out a face from a photo and uses it to cover their own face.
3D mask attack: An imposter wears a 3D mask designed to resemble the face of another person.

Estimation configuration#

Regardless of the platform, you can configure the LivenessOneShotRGB settings via the faceengine.conf file in the LivenessOneShotRGBEstimator::Settings section:

Parameter	Description
`version`	Specifies the algorithm version (`10` or `11`).
`deny2XLmode`	Enables or disables the `2XL` or `XL` mode.

On Linux, in the rsengine.conf file, you can configure the following parameters:

Parameter	Description
`liveness-depth-osl`	Enables or disables LivenessOneShotRGB estimation. The default value is `1` (enabled).
`liveness-depth-osl-threshold`	Specifies the LivenessOneShotRGB threshold value. The default value is `0.7`.

On Windows, in the registry under HKLM\Software\VisionLabs\RSEServer, you can configure the following parameters:

Parameter	Description
`LivenessDepthOSL`	Enables or disables LivenessOneShotRGB estimation. The default value is `1` (enabled).
`LivenessDepthOSLThreshold`	Specifies the LivenessOneShotRGB threshold value. The default value is `0.7`.

Camera Monitoring Component#

Camera monitoring is used to check the status of the camera.

Camera monitoring queries the following camera parameters:

firmware data;
operating status of infrared cameras–on/off;
RGB camera operating status–on/off;
camera serial number;
operation status of the entire camera–on/off;
camera temperature;
date of the last update.

An example of the contents of the registry in the monitoring section is shown below (Figure 4).

Example of registry contents in the monitoring section

RSE Server component#

The RSE Server is a WebSocket server that processes commands from external systems.

The RSE Server accepts requests and sends responses via WebSocket.

Request Format:

Operation request code (1 byte)
Additional payload (MessagePack or string)

Example of a request:

GET ws://127.0.0.0.1:4444/–establishing a WebSocket connection.

0–content of the message to start the session.

Response Format:

Operation response code (1 byte)
Additional payload (MessagePack or string)

Only one request can be processed at a time.

Depending on the type of integration required (selected at the discretion of the external system developer), you can configure RSE Server in the following ways:

RSE Server expects requests (presented in Table 5) to connect to the camera from the external system–set the cs_communication = msg-pack parameter;
RSE Server starts the process of receiving video stream and face detection process as soon as WebSocket connection is established –set the cs_communication = json parameter.

Table 5. Description of requests to RSE Server

Request Name

Request Code

Description

Payload

Possible responses to the request

RSE_START_CAPTURE

0

Starts the process of receiving a video stream and the process of detecting faces

No

RSE_CAPTURE_OK (54),

RSE_CAPTURE_META (55)

RSE_STOP

1

Stops all running processes

No

RSE_STOP_OK (50)

Depending on the type of integration selected (chosen at the discretion of the external system developer), the server response can be presented in two formats:

if the external system developer has set the cs_communication = msg-pack parameter, each response will arrive in msg-pack format and will contain the messageType field with the response code and some additional data fields (payloads) described in Table 6;
if the external system developer has set the cs_communication = json parameter, each response will arrive in json format and will be categorized into the message types described in Table 7.

Table 6. Responses to RSE Server requests with MessagePack response format

Answer title	Code	Description **	Payload
RSE_CAPTURE_OK	54	Captured set of video frames	— rgbFrame—RGB frame in uint8 array format; — rgbFrameWidth—RGB frame width in pixels in int format; — rgbFrameHeight—RGB frame height in pixels in int format; — irFrame—IR frame in uint8 array format; — depthFrame—Depth frame in uint8 array format
RSE_CAPTURE_META	55	Metadata of detected persons	— gotBestshot—indicator of whether bestshot was received, in bool format, returns: true—if bestshot was received; false—if bestshot was not received failureReason—the status or error code for liveness checks in int format (see error description in "Appendix 2. Status codes and error descriptions";) – bestshot—RGB frame, in uint8 array format: if gotBestshot=True, the response is an RGB frame, that passes all checks; if gotBestshot=False, the field is blank
RSE_STOP_OK	50	All processing has stopped. RSE Server is ready for new requests	No payload
RSE_UNKNOWN	51	The request was not recognized	No payload
RSE_INTERNAL_ERROR	52	An error occurred while processing the request	No payload
RSE_BUSY	53	Request denied because server is busy	No payload

Table 7. Responses to RSE Server requests with JSON response format

Message type

Description

Payload

visual

The type of response that is used for broadcasting the video stream to the user

– msg_type–the type of message returned (visual);

– img_b64–base64 camera frame;

– metadata–parameters of the returned image:

frame_size–image dimensions:
h–height of the image in pixels;
w–width of the image in pixels;
detections–coordinates of the detected person:
h–height of the frame of the detected face;
w–width of the detected face frame
x–coordinates of the upper left corner of the detected face frame

– y–coordinates of the upper left corner of the detected face frame

progress–displays the stages of Liveness of the detected person's background checks (percentage);
track_id–track identifier

bestshot

The type of response when a person is successfully found.

This frame can be used for subsequent processing (e.g. in an external face recognition system)

– msg_type–the type of message returned (bestshot);

– img_b64–face from camera frame in base64 format;

– metadata–parameters of the returned image:

frame_size–image dimensions:
h–height of the image in pixels;
w–width of the image in pixels;
detections–coordinates of the detected person:
h–height of the frame of the detected face;
w–width of the detected face frame
x–coordinates of the upper left corner of the detected face frame
y–coordinates of the upper left corner of the detected face frame
progress–displays the stages of Liveness of the detected person's background checks (percentage);
track_id–track identifier

WebSocket Client component#

WebSocket Client is an external component for interacting with RSE Server.

WebSocket Client is a JavaScript library for communicating with RSE Server via WebSocket. It uses the minimized binary serialization format MessagePack as a protocol library to encode and decode messages if the server returns responses in MessagePack format.

System setup#

This section provides general information regarding System setup and logging.

The System allows you to customize the following parameters:

General parameters (for more details see. "Appendix 1: General configuration parameters").
Image capture parameters (change in the rsengine.conf file);
Face detection parameters (change in the rsengine.conf file);
Parameters of IOU check execution - check of BBox face intersection on IR and RGB images (change in rsengine.conf file).

Image capture parameters, face detection parameters, and IOU verification parameters are fixed by default and cannot be changed by the user (administrator). Setting of these parameters is performed only by the copyright holder (VisionLabs LLC).

There are other .conf files included in the System distribution. It is not recommended to change parameters in these files, as it may disrupt the System operation. The System can be configured only within the instructions below.

System setup on Windows#

The System is configured through the Windows Registry.

Settings received by the server from the client are saved until the System is restarted.

When configuring the System via the Windows Registry, write the settings in the following path:

\*\* HKEY\_LOCAL\_MACHINE \ SOFTWARE \ VisionLabs \ RSEServer \*\*

The configuration parameters are described in Table 8 and Table 9.

When changing configuration settings, the new configurations overwrites the previous configurations.

To change parameters in the registry, find the corresponding parameter, make changes and apply them.

System settings on Ubuntu 24.04 x64 and Debian 10 x64#

The System is configured by changing data in the client configuration files in the distribution (server.conf and rsengine.conf).

To apply the client configuration settings, make changes to the server.conf and rsengine.conf files (Table 8, Table 9) and restart RSE Server.

To change parameters, make changes to the appropriate file and apply the changes.

Logging#

RSE Server entries logs to the console as well as to a Windows log file for collections under Windows.

Log files use the following file naming scheme: server_YYYYYY-MM-DD.log.

Appendix 1: General configuration parameters#

General parameters are changed in the registry (for Windows) files server.conf (Table 8) and rsengine.conf (Table 9). Windows registry configuration parameters are shown below (Table 10).

Table 8. Common configuration parameters in the server.conf file

Parameter name	Data type	Silent value	Description
`data-path`	`string`	`./data.`	Path RSE Server data directory. It is not recommended to change Parameter value.
`rsengine-conf-path`	`string`	`./client/rsengine.conf`	Path to RSEngine library config file. Relevant for setting up the System on Ubuntu 24.04 x64, Debian 10 x64, Armbian 23 and Windows OS using configuration files
`cs-communication`	`string`	`msg-pack`	The type of interaction between the server and the client. Depends on the selected System configuration. Can take the following values: `json`: the data type returned by the server is JSON; `msg-pack`: the data type returned by the server is MessagePack
`bestshot-format`	`string`	`jpg`	The returned image format of the bestshots. Selected based on the requirements of external software. Can accept the following values: `jpg`: JPEG format; `png`: PNG format
`save-bestshot-ondisk`	`int`	`0`	Saving bestshots to disk to the directory `save-bestshot-path/SaveBestshotPath`. `0`–do not save; `1`–save.
`save-bestshot-path`	`string`	`./bestshots`	The directory for saving the best shots when the `save-bestshot-ondisk/SaveBestshotonDisk` variable is activated.
`encrypt-bestshot`	`int`	`0`	Encryption of the bestshots when saving them. Not used in this version of the System. `0`–do not encrypt; `1`–encrypt.
`server-host`	`string`	`127.0.0.1`	IP address of the server on which to run to accept websocket connection. When using one copy, specify localhost; when using several running copies, specify the main server.
`server-port`	`int`	`4444`	Port on which RSE Server accepts connections
`log-level`	`int, [0, 3]`	`1`	The logging level filters log messages and has the following levels from 0 to 3: `0`–disable logging; `1`–logging information about work; `2`–logging warnings and information about work; `3`–logging errors, warnings and operation information.
`log-path`	`string`	`./logs`	Path to a writable directory for storing server logs
`log-file-rotation`	`int`	`0`	Daily log rotation `0`–disabled; `1`–enabled.
`continuous-bestshots`	`int`	`0`	Continue to receive bestshots in the session, even if bestshot has already been received `0`–disabled; `1`–enabled.

Table 9. Common configuration parameters in the rsengine.conf file

In the rsengine.conf file, the unique settings for each camera are separated into blocks.

Parameter name	Data type	Silent value	Description
`processor-strategy`	`string`	`IntelRealSense`	Camera System Mode: `IntelRealSense`–working with Intel RealSense camera; `VLSLunaCamera3D`–working with VLS LUNA CAMERA 3D; `VLSLunaCamera2D`–working with VLS LUNA CAMERA 2D.
`camera-monitoring`	`int`	`1`	Parameter enables/disables monitoring of the camera status. `0`–turns off monitoring; `1`–turns on monitoring
`camera-monitoring-delay`	`int`	`300`	Parameter sets the request frequency for the camera status from the monitoring service
`rgb-ir-match`	`int`	`0`	Using RGB and IR camera data to perform checks It is not recommended to change this parameter. `0`– off; `1`– on.
`check-eyes`	`int`	`1`	Using information about eye position and status for checking Liveness. `0`–off; `1`–on.
`check-mouth`	`int`	`0`	Using information about mouth status for checking Liveness. `0`–off; `1`–on.
`liveness-depth`	`int`	`1`	Using information about face volumetric on image when checking Liveness. It is not recommended to change this parameter. `0`–off; `1`–on.
`liveness-depth-osl`	`int`	`1`
`liveness-depth-threshold`	`float`	`0.0`	The minimum threshold for the Liveness value when checking face in the volumetric image. Threshold is set between 0.0 and 1.0 (0...100 for Windows), where: `0`–no check `0.1–high probability of missing a fake `1`–low probability of missing a fake, high probability to miss a real person
`liveness-depth-osl-threshold`	`float`	`0.7`	Minimum threshold for Liveness value while face checking Parameter is chosen analytically by the developers and is not recommended to be changed. The threshold is set in the range from 0.0 to 1.0 (0...100 for Windows), where: `0`–no check `0.1`–a high probability of missing a fake `1`–low probability of missing a fake, high probability to miss a real person
`rgb-coordinates-transfer`	`int`	`1`	Transferring the Bbox coordinates of a face from an RGB image to an IR image for further processing. `0`–off; `1`–on.
`iou-liveness-threshold`	`float`	`0.5`	The threshold for using IOU when building a Bbox. Parameter is chosen analytically by the developers and is not recommended to be changed. The threshold is set in the range of 0.0 to 1.0 (0...100 for Windows).
`quality-threshold`	`float`	`0.8`	Minimum threshold for evaluating image quality before checking Liveness. Parameter is chosen analytically by the developers and is not recommended to change. The threshold is set between 0.0 and 1.0 (0...100 for Windows).
`rgb-ir-match-threshold`	`float`	`1.2`	Face comparison threshold from IR and RGB images. Parameter is chosen analytically by the developers and is not recommended to be changed. The threshold is set between 0.0 and 1.0 (0...100 for Windows).
`margin`	`int`	`10`	Minimum space between the face box and the frame boundaries in pixels. The face must be at least 10 pixels from the frame border when performing a Liveness check, so that face information is not lost. 10...100 pixels
`suspicious-threshold`	`float`	`0.6`	Minimum image quality threshold at which the Liveness check will be performed. Parameter is chosen analytically by the developers and is not is not recommended to be changed. The threshold is set in the range of 0.0 to 1.0 (0...100 for Windows).
`light-threshold`	`float`	`0.9`	Minimum threshold for checking the quality of face illumination at image at which the Liveness check will be performed. Parameter is chosen analytically by the developers and is not recommended to change. The threshold is set in the range of 0.0 to 1.0 (0...100 for Windows).
`dark-threshold`	`float`	`0.93`	Minimum threshold for checking the quality of darkness on the face. image at which the Liveness check will be performed. Parameter is chosen analytically by the developers and is not recommended to change. The threshold is set in the range of 0.0 to 1.0 (0...100 for Windows).
`blur-threshold`	`float`	`0.94`	Minimum threshold for checking the quality of blurred face image at which the Liveness check will be performed. Parameter is chosen analytically by the developers and is not recommended to change. The threshold is set in the range of 0.0 to 1.0 (0...100 for Windows).
`yaw-threshold`	`int`	`15`	Maximum head tilt angle relative to the camera axis,, at which the Liveness check will be performed. Parameter is chosen analytically by the developers and is not recommended to be changed.
`pitch-threshold`	`int`	`15`	Maximum head rotation angle relative to the camera axis, at which the Liveness check will be performed. Parameter is chosen analytically by the developers and is not recommended to be changed.
`roll-threshold`	`int`	`10`	Maximum head rotation angle relative to the camera axis, at which the Liveness check will be performed. Parameter is chosen analytically by the developers and is not recommended to be changed.
`autoexp-rgb`	`int`	`1`	Enable auto exposure mode for RGB images. It is not recommended to disable this setting. `0`–off; `1`–on.
`autoexp-ir`	`int`	`1`	Enable auto exposure mode for IR image. It is not recommended to disable this setting. `0`–off; `1`–on.
`ir-stream-darkness-check`	`int`	`0`	Check for lack of image illumination in IR image.
`roi-enable`	`int`	`1`	Cropping the original frame to reduce the area of interest to improve the recognition quality. The preset parameters below limit the central part of the frame, where the face is least distorted. It is not recommended that this setting be turned off. `0`–off; `1`–on.
`roi-x`	`int`	`160`	Horizontal coordinate of the upper left corner of the area of interest. Specified from the upper left corner of the frame. It is not recommended to change this parameter.
`roi-y`	`int`	`0`	Vertical coordinate of the top left corner of the area of interest. Set from the upper left corner of the frame. It is not recommended to change this parameter.
`roi-width`	`int`	`320`
`roi-height`	`int`	`480`	Height of the area of interest. It is not recommended to change this parameter.
`frame-rotation`	`int`	`0`	The rotation angle of the camera frame. Possible values: `0`, `90`, `180`, `270`. For the location of the camera depending on the rotation angle of the video frame, see the diagram below (Figure 5)
`liveness-ir`	`int`	`1`	IR Liveness check. `0`–off; `1`–is on

Table 10. Windows Registry Configuration Settings

Parameter name	Data type	Silent value	Description
`DataPath`	`REG_SZ`	`{Path to system` `files}/data`	Path to RSE Server data directory. It is not recommended to change the value of Parameter.
`CSCommunication`	`REG_SZ`	`msg-pack`	The type of interaction between the server and the client. Depends on the selected System configuration. Can take the following values: `json`: the data type returned by the server is JSON; `msg-pack`: the data type returned by the server is MessagePack
`BestshotFormat`	`REG_SZ`	`jpg`	The returned image format of the bestshots. Selected based on the requirements of external software. Can accept the following values: `jpg`: JPEG format; `png`: PNG format
`SaveBest` `shotonDisk`	`REG_DWORD`	`0`	Saving the bestshots to disk to the directory `save-bestshot-path/SaveBestshotPath`. `0`–do not save; `1`–save.
`save-bestshot-path`	`string`	`./bestshots`	The directory for saving the best shots when the `save-bestshot-ondisk/SaveBestshotonDisk` variable is activated.
`EncryptBestshot`	`REG_DWORD`	`0`	Encryption of the bestshots when saving them. Not used in this version of the System. `0`–do not encrypt; `1`–encrypt.
`ServerHost`	`REG_SZ`	`127.0.0.1`	IP address of the server on which to run to accept websocket connection. When using one copy, specify localhost; when using several running copies, specify the main server.
`ServerPort`	`REG_DWORD`	`4444`	The port on which the RSE Server accepts connections
`LogLevel`	`REG_DWORD`	`1`	The logging level filters log messages and has the following levels from 0 to 3: `0`–disable logging; `1`–logging information about work; `2`–logging warnings and information about work; `3`–logging errors, warnings and operation information.
`LogPath`	`REG_SZ`	`C:\RSE\logs`	Path to a writable directory for storing server logs
`Processor`	`REG_SZ`	`IntelRealSense`	Camera System Mode: `IntelRealSense`–working with Intel RealSense camera; `VLSLunaCamera3D`–working with VLS LUNA CAMERA 3D; `VLSLunaCamera2D`–working with VLS LUNA CAMERA 2D.
`Camera` `Monitoring`	`REG_DWORD`	`1`	Parameter enables/disables monitoring camera status. `0`–turns off monitoring; `1`–turns on monitoring.
`Camera` `MonitoringDelay`	`REG_DWORD`	`300`	Parameter sets the request frequency for the camera status from the monitoring service.
`RgbIrMatch`	`REG_DWORD`	`0`	Using RGB and IR camera data to perform checks It is not recommended to change this parameter. `0`– off; `1`– on.
`CheckEyes`	`REG_DWORD`	`1`	Using information about eye position and status for checking Liveness. `0`–off; `1`–on.
`CheckMouth`	`REG_DWORD`	`0`	Using information about mouth status for checking Liveness. `0`–off; `1`–on.
`LivenessDepth	`REG_DWORD`	`1`	Using information about face volumetric on image when checking Liveness. It is not recommended to change this parameter. `0`–off; `1`–on.
`LivenessDepthOSL`	`REG_DWORD`	`1`	LivenessOneShotRGB estimation. We do not recommend to change this parameter. `0`–off; `1`–on.
`LivenessDepth	`REG_DWORD`	`0`	The minimum threshold for the Liveness value when checking face in the volumetric image. Threshold is set between 0.0 and 1.0 (0...100 for Windows), where: `0`–no check `0.1–high probability of missing a fake `1`–low probability of missing a fake, high probability to miss a real person
`LivenessDepth `OSLThreshold`	`REG_DWORD`	`0.7`	Minimum threshold for Liveness value while face checking Parameter is chosen analytically by the developers and is not recommended to be changed. The threshold is set in the range from 0.0 to 1.0 (0...100 for Windows), where: `0`–no check `0.1`–a high probability of missing a fake `1`–low probability of missing a fake, high probability to miss a real person
`RGBCoordinates` `Transfer`	`REG_DWORD`	`1`	Transferring the Bbox coordinates of a face from an RGB image to an IR image for further processing. `0`–off; `1`–on.
`IOULiveness`	`REG_DWORD`	`50`	The threshold for using IOU when building a Bbox. Parameter is chosen analytically by the developers and is not recommended to be changed. The threshold is set in the range of 0.0 to 1.0 (0...100 for Windows).
`Quality` `Threshold`	`REG_DWORD`	`80`	Minimum threshold for evaluating image quality before checking Liveness. Parameter is chosen analytically by the developers and is not recommended to change. The threshold is set between 0.0 and 1.0 (0...100 for Windows).
`RgbIRMatch` `Threshold`	`REG_DWORD`	`120`	Face comparison threshold from IR and RGB images. Parameter is chosen analytically by the developers and is not recommended to be changed. The threshold is set between 0.0 and 1.0 (0...100 for Windows).
`Margin	`REG_DWORD`	`20`	Minimum space between the face box and the frame boundaries in pixels. The face must be at least 10 pixels from the frame border when performing a Liveness check, so that face information is not lost. 10...100 pixels
`Suspicious` `Threshold`	`REG_DWORD`	`60`	Minimum image quality threshold at which the Liveness check will be performed Parameter is chosen analytically by the developers and is not is not recommended to be changed. The threshold is set in the range of 0.0 to 1.0 (0...100 for Windows).
`LightThreshold`	`REG_DWORD`	`90`	Minimum threshold for checking the quality of face illumination at image at which the Liveness check will be performed. Parameter is chosen analytically by the developers and is not recommended to change. The threshold is set in the range of 0.0 to 1.0 (0...100 for Windows).
`DarkThreshold`	`REG_DWORD`	`93`	Minimum threshold for checking the quality of darkness on the face. image at which the Liveness check will be performed. Parameter is chosen analytically by the developers and is not recommended to change. The threshold is set in the range of 0.0 to 1.0 (0...100 for Windows).
`BlurThreshold`	`REG_DWORD`	`94`	Minimum threshold for checking the quality of blurred face image at which the Liveness check will be performed. Parameter is chosen analytically by the developers and is not recommended to change. The threshold is set in the range of 0.0 to 1.0 (0...100 for Windows).
`YawThreshold`	`REG_DWORD`	`15`	Maximum head tilt angle relative to the camera axis,, at which the Liveness check will be performed. Parameter is chosen analytically by the developers and is not recommended to be changed.
`PitchThreshold`	`REG_DWORD`	`15`	Maximum head rotation angle relative to the camera axis, at which the Liveness check will be performed. Parameter is chosen analytically by the developers and is not recommended to be changed.
`RollThreshold`	`REG_DWORD`	`10`	Maximum head rotation angle relative to the camera axis, at which the Liveness check will be performed. Parameter is chosen analytically by the developers and is not recommended to be changed.
`AutoexpRGB`	`REG_DWORD`	`1`	Enable auto exposure mode for RGB images. It is not recommended to disable this setting. `0`–off; `1`–on.
`AutoexpIR`	`REG_DWORD`	`1`	Enable auto exposure mode for IR image. It is not recommended to disable this setting. `0`–off; `1`–on.
`IRStream` `DarknessCheck`	`REG_DWORD`	`0`	Check for lack of image illumination in IR image.
`RoiEnable`	`REG_DWORD`	`1`	Cropping the original frame to reduce the area of interest to improve the recognition quality. The preset parameters below limit the central part of the frame, where the face is least distorted. It is not recommended that this setting be turned off. `0`–off; `1`–on.
`RoiX`	`REG_DWORD`	`160`	Horizontal coordinate of the upper left corner of the area of interest. Specified from the upper left corner of the frame. It is not recommended to change this parameter.
`RoiY`	`REG_DWORD`	`0`	Vertical coordinate of the top left corner of the area of interest. Set from the upper left corner of the frame. It is not recommended to change this parameter.
`RoiWidth`	`REG_DWORD`	`320`	Width of the area of interest. It is not recommended to change this parameter.
`RoiHeight`	`REG_DWORD`	`480`	Height of the area of interest. It is not recommended to change this parameter.
`LogFileRotation`	`REG_DWORD`	`0`	Daily log rotation `0`–disabled; `1`–enabled.
`Continuous` `Bestshots`	`REG_DWORD	`0`	Continue to receive bestshots in session even if bestshot has already been received `0`–off; `1`–on.
`FrameRotation`	`int`	`0`	The rotation angle of the camera frame. Possible values: `0`, `90`, `180`, `270`. For the location of the camera depending on the rotation angle of the video frame, see the diagram below (Figure 5)
`LivenessIr`	`int`	`1`	IR Liveness check. `0`–off; `1`–is on

Location of the VLS LUNA CAMERA 2D camera depending on the rotation angle of the video frame

Appendix 2. Status codes and error descriptions#

Status codes and descriptions of failureReason errors in the RSE_CAPTURE_META response payloads when performing a Liveness check are summarized in Table 11.

Codes are common to msg-pack and JSON responses.

Table 11. Status codes and description of failureReason errors in RSE_CAPTURE_META response

Status Code	Description
0	There are no errors, the frame passes checks
1	Incorrect RGB frame
2	Incorrect Depth frame
3	Incorrect IR frame
4	Face wasn't detected
5	Face wasn't detected (face too small in frame)
6	The detected face doesn't pass one of the configuration parameters
7	It is impossible to estimate the face in the frame by 5 points
10	The face in the frame is cropped
11	Face rotated—eye distance is too short
13	Failed to normalize RGB frame
14	Failed to normalize Depth frame
15	Failed to normalize IR frame
16	Incorrect head position
17	Eyes are closed
18	Neutral face expression of the mouth muscles is necessary
19	Liveness frame Depth check was failed
20	Liveness IR frame check was failed
21	Poor frame quality
22	RGB frame is too bright
23	RGB frame is too dark
25	Image is blurry
26	LivenessOneShotRGB estimation failed
28	Liveness check of RGB and IR frames comparison is in progress
29	Liveness check IR frame without illumination
31	Failed to recognize face on the frame
32	Failed to detect face on IR frame
33	Low quality Depth frame
34	Several faces with overlapping BBox zones detected