FastLine
Introduction
The GBS FastLine is a software application for authentication in waiting lines. It uses facial identification quickly and accurately to make people identified faster than by the document checking process performed by a human operator. Using FastLine, it is possible to recognize, identify and register individuals in a line automatically.
This manual is updated for FastLine version 1.5.1.
Application Versions
GBS FastLine is available in two versions:
Desktop Standalone
This version is for full use in a desktop environment, without the need for external tools or requirements.
GBS FastLine was designed as a service, and its desktop version is recommended for testing, validation and proof-of-concept procedures, or for trivial use cases.
In this document this version will be referred to only as Desktop.
Services
In this version, GBS FastLine is provided as a service and must be controlled by an external application through its API. This version also provides means for external supervision.
Software License
GBS FastLine requires a software license to operate. The license is not tied to any hardware address (such as MAC Address) and does not expire. The license must be installed in: C:\ProgramData\Griaule, according to the instructions present in the license manual.
If further assistance is required, contact Griaule support.
FastLine Initial Installation and Configuration
The FastLine installer has a configuration tab, GBDS Settings:

GBDS Settings
GBDS URL Address
URL address of the GBDS server. Example: http://192.168.0.1:8085.
Username and Password
Credentials used by FastLine to authenticate with GBDS.
User Interface
Starting the Application
When starting FastLine, the Home Screen will be displayed:

Adding Profiles to the Database
This section shows how to populate the local database.
Retrieving from GBDS
The form Load base from GBDS, shown below, can be used to retrieve profiles from GBDS. Profiles can be filtered by biographical keys. If the filter is left empty, all available profiles will be imported.

Local Registration
The button Capture Photo allows the user to register a new person in the local database. When selecting this option, the image capture window will open:

The Desktop version allows registration by capturing live images, or by importing image files already saved.
The Services allows registration by importing image files, but not by live capture. This version is focused on external uses, for which a database already populated with profiles is expected.
Viewing Profiles
The list of profiles is displayed in the sidebar, and shows all profiles available for detection. The number of profiles is shown at the top of the list.

The size of the displayed list can be modified in the application settings. Hovering the mouse pointer over a profile shows its photo. Profiles can be selected or deselected by clicking on them.
Deleting Profiles
To delete one or more profiles, select them by clicking in the profile list and press the Delete.
Once a profile is deleted, it cannot be recovered.
Application Settings
To configure the application, click Logout. on the home page:

On this screen, the user can configure the detection operation, as well as the camera to be used.
Default Workflow
The default workflow for using FastLine is as follows:
Log in
Populate the database
Start detection
Finish detection
Check the results
Export the PDF with the results.
Detection
Detection Screen
Error in the Federal Revenue Detection Screen is the core of GBS FastLine. On this screen, the user can view the images captured by the camera, as well as the people already identified and unidentified.

Performing Detections
Detections can be started through the interface of the Desktopversion, or through the API, in the Servicesversion. Once started, the application will begin recognition through the configured camera. Each time a frame of the live image matches a profile in the database, the event will be recorded and a notification may be sent (depending on the application settings).
Each profile can be recognized only once: When a profile is recognized, it is removed from the watch list.
It is possible to detect more than one face at once, reduce the camera detection area, specify other camera resolutions, switch between cameras, change the identification threshold, and other features, through the application settings.
Detections are performed in detection sessions, a concept discussed below.
Detection Session
All detection processes must occur within a Detection Session, these sessions can be created by the user through the interface or the API. Once created, sessions can be started, paused, resumed and finished. While not finished, sessions can have settings and data changed. Once finished, the session generates a detection report that can no longer be altered.
A Detection Session can be seen as a report that is being written. When complete, it becomes an immutable detection report, ensuring data consistency.
Each detection session has its own UUID (Universally Unique Identifier, in English, Universal Unique Identifier), called SGUID (Session Global Unique Identifier, in English, Session Global Unique Identifier)
Detected List
Error in the Federal Revenue Detected List shows the people who matched with the registered people since the beginning of the session:

Unidentified List
Error in the Federal Revenue Unidentified List shows the people who did not match with the registered people since the beginning of the session:

Results Report
The user can see the session status on the Report Screen:

Once the detection session ends, the detection list becomes an immutable report. The report is automatically saved in a PDF or JSON file. The report format and the location where it is saved are determined in the application settings. In the Desktopversion, the application can be configured to automatically show the report when the session is finished.

Generating Report While Running
You can generate a report while FastLine is running. This partial report is only available if the configuration parameter savePdfRunning is set to true in the config.propertiesfile. When this parameter is true, a button called Export as PDF will appear on the detection screen. You can click the button to generate the report.

External Notification
When FastLine detects a face, it will display the acquired face image and the reference face. Other information, such as the person's name and score are also displayed. The matching information can also be sent to a given URL through the configuration desktopStandalone.notifyUrl.
To modify the configuration, go to the FastLine folder, access the file conf/config.properties and change the parameter desktopStandalone.notifyUrl to the URL that will be notified.
After FastLine performs a match, it will display the information in the interface and notify the configured URL with the following JSON:
Note that the values of profileImageByteArray, template and queryImage will be bytearrays in base64 format.
The JSON fields are:
id: FastLine ID, defined by the configuration
desktopStandalone.notifyId.status: Indicates whether there was a match or not. It can return
MATCHorNOT_MATCH. When it returns the valueNOT_MATCH, the JSON will not have amatchSummary.template: Image template ByteArray in GBDS.
tguid: Unique transaction ID in GBDS.
name: Person's name. If no biographical information is available, this field can be blank.
document: value of the key defined in the field
key.key: Person's key in GBDS.
profileImageByteArray: ByteArray of the image in GBDS.
score: Match score.
timestamp: Timestamp of the match.
queryImage: ByteArray of the image captured by FastLine.
Last updated
Was this helpful?

