Sightcorp logo

Face Analysis Dashboard Solution

Powered by Sightcorp and Skyfii

  • Plug-and-play – no development needed
  • Detect and analyze multiple faces
  • Access real-time, accurate audience insights
  • Easy-to-use dashboard

Request Free Trial

Face Analysis Solution

This integrated solution from Skyfii and Sightcorp empowers you with accurate, real-time insights into your audience’s spontaneous behavior, interests, and demographic profile. It puts actionable data at your fingertips, enabling you to engage your customers, optimize your business, and make smarter data-driven decisions.

All Features in One Solution

  • Plug-and-play
  • Face detection and people counting
  • Age, gender and mood estimation
  • Viewers vs. OTS
  • Attention time
  • Heatmapping
  • CMS integration
  • Reporting dashboard
  • Data processed locally
  • Privacy by default: face blurring

The Dashboard

The integration between Sightcorp’s face analysis technology and Skyfii’s dashboard enables you to ingest, visualize, and segment your DeepSight Toolkit data using Skyfii’s People Counters Report – giving you new ways to develop a deeper understanding of your visitors.

How will you benefit?

Using almost any camera, you can anonymously detect and analyze the demographic profiles of your visitors and view your audience data in real-time in an easy-to-use interface. This integration provides you with a deeper understanding of your visitors and enables you to derive actionable insights from your data.

Interested?

Get started right away with special POC pricing!
Contact Us

Technical Specifications

The table below shows how FaceMatch SDK performs on the Labelled Faces in the Wild (LFW) dataset:

FPRTPRThreshold (Inverse of distance)
0.10.99900 ±0.002130.55448
0.010.99667 ±0.005370.59791
0.0010.99367 ±0.006050.62989

FPR = False Positive Rate
TPR = True Positive Rate

These results are an indication only and are based on the specific dataset Labelled Faces in the Wild. Customers can expect similar performance, with possible variations due to hardware and the availability of annotated data.