top of page

Facial Validation

In this section you will find the explanation of the basic principles of facial validation video analytics. Unlike classic facial recognition analytics for access control, facial validation analytics is much more advanced in its operation.

Principle of Operation

This video analytics tool is designed to generate specific alerts when individuals not registered in a facial recognition database cross a pre-designated area. Unlike traditional facial recognition systems, which trigger events by identifying people already registered in the database, this system operates in reverse. In other words, alerts are triggered when it detects individuals who are not part of the database,

Opening Configuration Parameters

To open the analytics configuration menu, stop all analytics that are currently running, and 1) click on the analytics configuration icon 2) select the analytics configuration file 3) click to expand the analytics corresponding to the desired camera.


Locate the parameter named 'face_validation_config_params' and click to expand it,


Explanation Configuration Parameters

Al hacer click en el parámetro de  face_validation_config_params se muestran los parámetros de configuración de la analítica,

  • enable:  set to 1 to activate the analytics (always leave it at 1)

  • show_positive_recognition: set to 1 if you want the analytics to show positive recognition events when someone is recognized in the database. If set to 0, the analytics will not show positive facial recognition events. 

  • show_negative_recognition: set to 1 if you want the analytics to show negative facial recognition events, that is, when a person was not recognized in the database. It is recommended to always leave it at 1. 

  • user_lost_for_negative: set to 1 if you want the analytics to validate people who are not in the database when they have disappeared from the camera view. Set to 0 if you want the analytics to validate people who are not in the database when they are still in camera view. 

  • bbox_min_size:  Minimum length in pixels that a face must have to be considered in the validation. It is recommended to leave it at 30. 

  • min_frames_in_zone_for_negative:number of samples that the face must be present in the video to be validated as a negative face. This parameter must be calibrated depending on the camera perspective. You can start with a value of XXXXX and observe the behavior. If you see the faces turn red too quickly increase it until you see the face turn from yellow to red in enough time.  The idea is that this value is as large as possible without the faces leaving the camera view without being validated in red or green.

  • num_frames_lost_for_negative: number of samples so that a face is out of view of the video and generates an alert if it is not validated. It is recommended to leave this value at 20. 

  • similarity_match_percentage:  Minimum similarity percentage that a face from the video must have with a face from the database to be considered a facial recognition event. It is recommended to leave it at 50 and calibrate according to the place where the analysis is installed.   The smaller the value, the more likely the system will make positive recognitions, but it is also possible that it will make associations with wrong people or false positives.  The larger the value, the more strict the system will be to recognize people in the database, but it is also possible that people who are in the database will not be recognized.  

Setting Up Facial Validation Zone

The parameter 'face_validation_zone' determines the area where faces should be located for the system to analyze them. Click the 'Select Zone' button to open a view of the camera video and configure the zone,


The video view should open on the right side and from there you can create the facial validation area. Remember that this area is where the faces that you want the system to validate must pass.  

If the video does not open, please check the camera settings, as there may be an issue connecting with the camera.

Open Existing Database

If you have already created a face database, you can open and edit it by going to the Edit Database section, selecting the database, and clicking on Open,


Depending on the number of faces you have in the database, it may take a few seconds for the panel on the right to open the faces registered in the system. To learn how to edit the database, please go to the section Using the Database Editor.​

If you need to create a database, this can be done in two ways:

  1. Create database manually

  2. Create database by importing xlsx file

The sections below explain these procedures

Delete Existing Database

If you want to delete an existing database, go to Edit Database, select the database you want to delete, type the key in the sectionKey to delete, and clicking onDelete. Ask us for the password to delete. 


Depending on the number of faces in your database, it may take a few seconds for the panel on the right to open, displaying the faces registered in the system. If you need guidance on editing the database, please refer to the 'Using the Database Editor' section.

To create a database, you have two options:

  1. Create a database manually.

  2. Create a database by importing an xlsx file.

The sections below provide detailed explanations for these procedures.

Create Database Manually

To manually create a database, navigate to the 'Create New Database' section. Enter the desired name in the white box (or leave the default one assigned by the system), and click the 'Create' button


This will open a new database in the editor on the right panel. You can start adding people by following the instructions in the Database Editor Management section. The next time you access the analytics configuration menu, the created database should appear in the Edit Database section, and you must open it from there to edit it

Create Database Importing .XLSX

  1. Create a folder with the name of your database, for example, "ex_facedb". Make sure the folder name does not contain spaces.

  2. Inside the folder, place all the photos of people's faces. The photos should meet the following specifications:

    • The .png extension is recommended, but .jpeg is also acceptable.

    • The filename should not contain spaces, for example, "pedro_gomez.png" or "catalinaPerez.png".       

    • Inside the folder, place all the photos of people's faces. The photos should meet the following specifications:

    • The .png extension is recommended, but .jpeg is also acceptable.

    • The filename should not contain spaces, for example, "pedro_gomez.png" or "catalinaPerez.png".

    • The image should be adjusted to the face and ideally have approximate dimensions of 400 px x 400 px. This is not a strict measure, meaning you can use images of 300 px x 300 px or 600 px x 650 px, and they don't have to be exactly square.

    • For better system performance, the facial image should be frontal, as shown in these examples:"


3. Inside the folder, create or copy a .xlsx file with the same database name, in this case, ex_facedb.xlsx. If you are working from the analytics server PC on Ubuntu Linux, you can use the LibreOfficeCalc program for this task. Ensure that when saving the file, it is saved with the extension XLSX, as other types of extensions are not compatible with the system. At this point, your folder should contain both the xlsx file and the images, with both having the same name.


4. In the Excel file, in row 1 create the column header with the following names. Be careful that the names must be exact

  • Yam

  • Lastname

  • Identifier

  • Image 1

  • Image 2

  • Image 3

  • Image 4

  • Image 5

For each person you want to add to the database, enter a row with the corresponding information.

  • The Name, Lastname and Identifier information is optional. 

  • Identifier use it as an identifying word such as Apto 305, Company Name, etc. 

  • It is mandatory that the row have in Image 1 the name of the image file of that person, for example pedro_gomez.png. If that person has other images associated, you can add them in Image 2, Image 3, etc. If you don't have one, you can leave these blank. 

The file should look like this, 


5. If I created the folder with the file and images on another computer, copy it to a USB, connect it to the mini-pc server and copy it to the folderDocuments

6. Open Video Analyzer and go to the sectionImport database from file. At this point, the folder you created in the previous steps should appear in the list. (If it does not appear, check that the name of the folder and xlsx file are the same and that the folder is in the Documents folder. If you were in the analytics configuration menu open when you created the folder, reopen the menu analytics setup to refresh values)


Click on Open, on the right panel, you should import the database with the data contained in your folder with the Excel file and images. Depending on the number of people in the file, this may take a few seconds,


Notice that at the top of the Database Editor, the number of people registered in the database is displayed. It's advisable to compare this number with the number of people in your Excel file. If you observe a discrepancy, it's likely that the system failed to import it because the image file name in the 'Image 1' column is incorrect, or the image wasn't in the folder.

IMPORTANT: After this point, the database is already imported and saved within the system. Therefore, if you need to edit it by adding/removing people, you should open it as explained in the 'Open Existing Database' section. If you need to export it again to a file, follow the instructions in the 'Export Database to File' section.

IMPORTANT: After importing the database, as it is already saved within the system, if you wish, you can now delete the folder you created in Documents and also from the recycle bin.

Export Database to File

If you want to export an existing database to an Excel file, you can do so from the Database Editor. Select a name and click Export File 


This will create a folder in Documents with the database data. 

Using the Database Editor

The database editor allows you to Add, Edit, and Delete people from the database.


Add a New Person:

To add a new person, click on the "Add" button. This action will open a new card with fields. Click on "Upload Image" and select the person's image. Ideally, use a PNG format with a frontal view and dimensions of approximately 400 px x 400 px. After adding the image, fill in the optional fields: First Name, Last Name, and Identifier. If you don't provide this information, the system will register the person as unnamed. Note that the Identifier field can include additional information such as Apartment, Company, etc.


To edit a person in the database, locate the box in the list and click to expand it. Make the necessary changes and click the green "Keep" button. If you wish to change the associated image, you'll need to delete the person and create a new entry.


To remove a person from the database, locate the box in the list and click to expand it. Click on the orange "Delete" button.


If you want to expand all people cards in the database, use the "Expand" button. However, exercise caution if you have many people in the database, as it may take several seconds to load all the images. We recommend opening and closing the specific card you want to edit rather than expanding all at once.

Run Video Analytics

After making all changes to the parameters or database, click the lower green Save button.


Click on the 'Play' button below. If the system is configured correctly, you should see the camera view with the facial validation area.


At this moment, we recommend conducting the following tests to verify the correct functioning of the system.

Have a person with a record in the database walk towards the validation area. The system should recognize them and change the face box color from yellow to green. If it doesn't recognize them, please verify the following:

The image in the database is frontal and meets the recommended specifications.

The similarity match percentage is not too high. You can verify this if the person stands in front of and close to the camera. If it recognizes them in that case, the percentage might be high. However, we do not recommend lowering it below 50% because it increases the possibility of false positives.

Have a person without a record in the database walk towards the validation area. After some time, the system should change the face box color from yellow to red.

If you encounter any issues, please contact our technical support team

bottom of page