
Facial recognition is perfect for access control systems. Build into Smart Building security systems, turnstiles, gates, even vending machines, as well as Smart Home security and personalization applications.
IntelliVision’s Face Recognition software is a fast, accurate, deep learning-based facial recognition solution for OEMs, integrators and developers that can detect faces of all ethnicities, without racial bias, and recognize them from a database of images. Optimized for working in-camera with restricted CPU power it can also be used on-server, or in-cloud.
IntelliVision facial recognition software searches an existing database of faces and compares them with the faces detected in the scene to find a match. Face Recognition detects faces in the camera's field of view - as many as 15 at the same time - and matches them against faces previously stored in the database. Anti-spoofing is provided through "liveness" testing without the need for a stereo or 3D camera. Faces can be enrolled in the database from existing still images or from the video camera itself.
Facial recognition is perfect for access control systems. Build into Smart Building security systems, turnstiles, gates, even vending machines, as well as Smart Home security and personalization applications.
Trained on millions of images from across the world, faces from multiple ethnicities are easily detected. Faces can be enrolled from still images, live and pre-recorded video.
Very low FRR and FAR rates. Confidence level can be adjusted up or down and face recognition improved with additional training.
Using AI and deep learning, IntelliVision's face recognition has achieved accuracy benchmarks better than industry leaders like Google and Facebook. It scores the following accuracy in the leading public test databases – LFW: 99.6%, YouTube Faces: 96.5%, MegaFace (with 1000 people/distracters): 95.6%.
Facial Recognition accuracy exceeds 99% on public standard data set.
Face recognition in real time or off-line.
Recognition is available in both real-time and off-line modes and enrollment is available from both video and still images. Facial recognition is achieved by analyzing multiple images per face with millisecond response times depending on system resources.
Face Recognizer is available with a REST API/SDK for OEM partners and application builders. Easy integration of alerts is achieved through http/JSON and an open architecture.
For OEM partners and application builders.
Runs on Linux, inside camera, cloud solution and embedded systems.
Runs on Linux or Windows for server-based deployment, 1-16 cameras per PC based on CPU capacity. In-camera/embedded, facial recognition software works with various camera platforms and popular chipsets running Linux. On-cloud it is available as a Web Server Application and through Cloud Web Services API Interface.
Perfect for access control applications either in-camera or on-server. Identify persons of interest and unwanted persons
Liveness testing with 2D cameras, and models developed with multi-ethnic and gender datasets to ensure no built-in bias
Very high accuracy in tests with YouTube, LFW, Megaface. Tunable confidence level and continuous training