Home / AI Products / Face Recognition

Face Recognition

IntelliVision’s Face Recognizer™ product is a highly accurate Face Recognition solution that uses a stored database of faces to detect, recognize and record people’s faces that appear in a camera’s field of view.

AI-Based Face Detection, Logging and Search

Face Recognizer’s detection capability searches an existing database of faces and compares them with the faces detected in the scene to find a match. Face Recognizer records faces from the camera and detects “people of interest,” providing real-time alerts upon detecting certain faces in the scene.

Key Features of Face Recognizer

  • Detect and log faces
  • Recognize faces (with pre-registration)
  • Search for similar faces from a single camera or across multiple cameras
  • Detect any matches with faces on the “watchlist” database and provide alerts
  • Create an automated log of people in the scene which can be used for forensic investigations
  • Face recognition accuracy up to 99.6% on public standard data set

For security professionals and Smart Home users. Quickly scan people present in the scene to shortlist, target and identify potential miscreants.

Identify and capture human faces from still images, live video and pre-recorded video clips.

Improve security at government, commercial and industial sites. Improve customer service and security at banks, casinos, retail stores, hotels and restaurants.

 

Watch a Demo

Face Recognition – Accurate and Fast

Using a combination of AI, CNN (convolutional neural network) and Deep Learning, Face Recognizer has achieved accuracy benchmarks comparable to 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%.

High Accuracy

Face Recognition accuracy as high as 99.6% on public standard data set.

Real Time

Recognition is possible in both real time and offline modes.

Recognition and detection is possible both in real time and off line and recognition and enrollment are available from both video and still images. Recognition in video mode is achieved by analyzing multiple images per face and in video mode recognition is achieved in less than 1-2 seconds.

Face Recognizer is available with a Rest API/SDK for partners and external systems. Easy integration of alerts is achieved through http/XML and an open architecture.

Available with API/SDK

For partners and external systems.

Available on

Windows, Linux, Inside camera, Cloud solution and embedded systems.

Runs on Windows or Linux for server-based deployment, 1-16 cameras per PC based on CPU capacity. In-camera/embedded, Face Recognizer works with various camera platforms and popular chip sets, running Linux or Android. On-cloud it is available as a Web/Server Application and through Cloud Web Services API Interface.

Why Face Recognizer?

AI-based Computer Vision Technology

Enable security professionals to shortlist, target and identify intruders, loiterers and potential miscreants

Continuous Logging of People and Faces

Create an automated log of people in the camera or scene which can be used for forensic investigations

Highly Accurate Face Recognition

Enable automated matching against a watchlist with real time alerting

Copyright 2017. All rights reserved. Back to top