← Back to Additional Modules in Xeoma

Professional Face Recognition by Xeoma for personal and business uses

AI-based brain-inspired Face Detection and Face Recognition is available in Xeoma for personal and business use

Face Recognition by Xeoma:
personal and business uses

This is how Face Recognition module icon looks like

Xeoma’s Face Recognition is a powerful and affordable tool for automated finding people’s faces in a cameras’ live stream, recognition of detected faces in realtime (comparison of detected faces with faces from database), tracking selected individuals, or reacting to known or unknown persons.

 

Face Recognition in Xeoma works in different conditions, for different tasks

 

TYPICAL USES

Face Recognition is the process of automated searching for human faces in camera stream, and establishing if the found face belongs to a known person.
It can be used in
• Police, for searching city cameras for missing people;
• Security Access Control, for automation of entry for employees or authorized visitors (for kindergartens, office buildings, residences, restricted access areas in military or hospitals etc);
• Business Optimization, for recognizing returning customers (for example, for integration with tailored ads);
• Visitors Counting, for counting visitors of an establishment;
• Video Phones, for face-recognition-based video doorbell for access control;
• Crowd Detection, for detection of people gathering or a queue;
• Work Time Management, for detection of less people in camera image than there should be (in office, production line)
• In Privacy Making, to dynamically blur people’s faces
• In various other cases, where you need the system to know that the object in camera image is a human being (for example, ignoring Motion Detector’s alerts triggered by people while leaving all other events)

 

WHY XEOMA’S FACE RECOGNITION IS BETTER

Xeoma's Face Recognition works on your computer and saves network bandwidth by not sending images to a Cloud

Saves bandwidth:
All done on your machine, no need to connect to any cloud servers.

Xeoma's Face Recognizer works with realtime video streams

Realtime video:
Works with real-time video streams. The more fps, the better!

The Face Recognition feature is in two options, for different tasks and budgets

Cost-effective:
One-time payment. You don’t need to pay per image.
Two options, for any budget

 

WATCH VIDEO ABOUT FACE RECOGNITION

 

 

FACE RECOGNITION: MODULE FEATURES

FACE RECOGNITION: SETUP GUIDE

 

 

HOW IT WORKS

Xeoma face recognition can operate in one of two independent modes – “Statistical analysis” (avg. 70% recognition accuracy) or “Artificial intelligence” (avg. 90% recognition accuracy). Starting from beta version 23.12.7, the “Artificial intelligence using CNN (ConvNet)” mode is available – it allows you to more accurately recognize the faces of people of Asian appearance. Please note that technically this is the 3rd method of face recognition, but in fact it is only an additional option in face recognition using artificial intelligence algorithms.

The statistical analysis option in Face Recognition is cheaper but requires finer conditions

The recognition methods in Face Recognition module are mutually exclusive – only one can be selected and used for all cameras. The database of faces created for a recognition method can only be used for this method. Each method has its advantages and special treats that can be summarized in a table below:

Statistical analysis

professional_face_recognition_xeoma_artificial_intelligence_statistics_2

• Simpler algorithms, average recognition accuracy (successful rate) 75%;

• Mostly for indoor use;

• Successfully ignores face modification like glasses and beards;

• Available in the Xeoma Pro edition;

Unlimited number of faces;

+ Available search for people by their names through archive recordings (or overview of all episodes with unrecognized people);
– Search for faces by photo unavailable

The statistical analysis option in Face Recognition is cheaper but requires finer conditions

See more in Setup Guide

Artificial Intelligence

The Artificial Intelligence option in Face Recognition is working indoors and outdoors and gets a higher recognition rate

• Advanced algorithms, high-speed processing and analysis, average recognition accuracy (successful rate) 90%;
• For indoor and outdoor use;
• Faster identification of several faces in camera’s field of view;
• Can work with face modification: glasses, hairstyles, hats;
• Available in Xeoma Pro edition (number of faces = number of Pro licenses);
• Can be purchased separately (Additional module license) and used over Xeoma Pro or Xeoma Standard licenses;
• Number of faces depends on license;
+ Available search for people by their names through archive recordings (or overview of all episodes with unrecognized people);
+ Available search by a photo through archive recordings (requires Additional license for this feature);
+ Available means to detect new, unique visitors;
+ Available means to synchronize databases between several servers

The Artificial Intelligence option in Face Recognition is working indoors and outdoors and gets a higher recognition rate

See more in Setup Guide

Artificial intelligence using CNN (ConvNet)

Asian face recognition with artificial intelligence

Available starting from beta version 23.12.7
• Improved accuracy of Asian face recognition;
• Average recognition accuracy is 90%;
• Works equally well indoors and outdoors;
• It is not possible to work with appearance modifiers: glasses, hairstyles, hats;
• Available in Xeoma Pro mode (number of persons for training = number of Pro licenses);
• Can be purchased separately (as a license for the Additional Module) and used on top of Xeoma Pro or Xeoma Standard licenses – in this case the number of persons is summed up;
• The number of available faces depends on the license;
+ Available search for people by their names through archive recordings (or overview of all episodes with unrecognized people);
+ Available search by a photo through archive recordings (requires Additional license for this feature);
+ Available means to detect new, unique visitors;
+ Available means to synchronize databases between several servers

Asian face recognition with artificial intelligence

 

xeoma_software_advices The Face Recognition module can save reports in spreadsheet CSV files (tick the corresponding option in its settings for that).
CSV spreadsheets are used to form a powerful reports system. You can import CSV reports into programs like Excel or LibreOffice and build reports and graphs of any sophistication level there. Alternatively, CSV can be imported into mysql and used to form any kind of reports with the help of mysqladmin web interface – or just make a simple several-lines-of-code script for an automated reporting. See examples and guides in the Internet.
Important tip about Face Recognition Xeoma’s other modules might be useful for some of the Face Recognition tasks: use the “FaceID” module for double authentication, “Visitors Counter” for simpler people counter, “Object Recognizer” for reaction to animals or vehicles instead of humans. See more in our ‘Support’ section for more guides.

 

NO SPECIAL EQUIPMENT REQUIRED

face_recognition_no_special_equipment

No special equipment or a powerful standalone server is required. Recognition load is on average 20% more than that of a regular camera in the program. Use our calculator here.

 

face_recognition_no_special_cameras

No special cameras with embedded recognition detectors required – high quality video stream and proper angle of position are enough. Recognition processes are conducted on Xeoma’s side. Point the camera as perpendicularly as possible towards the faces, and make sure that the face is in the camera’s field of view for at least a few seconds. More about configuration of face recognition

 

face_recognition_software_choice

Affordable price. Depending on the required conditions and the desired result, you can choose Xeoma Pro with basic Face Recognition, or use advanced “Artificial Intelligence” option with Xeoma Standard and the additional “Face Recognition” module. Check prices for Xeoma licenses and Additional modules here

 

HOW TO TEST

1. Launch Xeoma. Make sure your Xeoma is in a trial edition or activate a PRO edition license.
2. Add a camera or let Xeoma add a default one for you.
3. Add a Face Recognition module to the chain.
4. Select a method to work with – Statistical analysis or Artificial Intelligence.
Remember that the methods work independently, for each method you need to create its own database of faces to recognize.
5. Train the module to know several people. See how it works when they appear in camera image.
See detailed setup guide here

 

 

FREE TRIAL OF XEOMA

Try Xeoma for free! Fill in the fields below and you will get an email with a demo license for the Xeoma Pro edition and all Additional modules, which includes the ‘Face Recognition’ module with both face recognition methods.

To do that, enter your name and your email to send the license to in the fields below, and click the ‘Get Xeoma free demo licenses to email’ button.




You can read our privacy policy here
 

 

Have any questions? Need help? Please contact us! We will be happy to help!

Important tip about Face Recognition Do you need something else? We can develop it and add it into Xeoma as the paid development. See details

 
February 12, 2020; updated November 23, 2020

Read also:
Additional modules in Xeoma.
Buy Xeoma’s Additional modules
More about Face Recognition
More about face-based search through recordings
Required hardware calculator
FaceID. Double Authentication with Face Recognition and a QR code/Smart Card