Sightcorp logo

Face Search

  • Search for faces in your database
  • Use it for real-time video face search
  • State-of-the-art deep learning model

Start Free Trial Learn more

Easily find similar-looking faces

Given a collection of faces and a new face as a query, our Face Search functionalities will return a collection of similar faces.

Benefits

Find similar-looking faces in a database or in a video stream and then group or cluster them together.

Face Blur Software

Loyalty Programs

Search your database for VIP clients and build strong customer relations.

cctv

Security

Prevent fraud by searching image database for fraudsters.

 

liveness detection

Media

Find similar looking faces in large image databases & group them together.

Start Free Trial Contact us

Features

Why Sightcorp Face Search software?

We develop patented proprietary AI Software solutions. We develop patented proprietary AI Software solutions. With our extremely robust and accurate face detector, you can start blurring faces anywhere with ease!

Simple to use

Robust & Accurate

 

easy-to-integrate

Easy to integrate

 

affordable

Affordable

 

Product

FaceMatch

FaceMatch is a state-of-the-art software that enables users to search
and verify faces. FaceMatch is designed to help businesses build strong customer identification programs and improve client experiences.

FaceMatch can detect faces from any angle & distance and perform accurate demographic analysis on the edge!

Benefits

  • 100% Developed in-house
  • Real-time analysis
  • Highly accurate pre-trained model
  • State-of-the-art

Testimonial

We are using and heavily promoting Sightcorp’s Toolkit because of its stability, accuracy and very easy installation and hardware configuration. The real-time aggregated data is immediately accessible through the reporting dashboard, which enables us to scale with ease.

─ S. Ahmedov, CEO OmniChannel

 

Face Search Technology

What is face search?

Face search is a function that refers to finding a similar face in either a database of pictures or in a video stream.
Finding faces similar to one another in images can be done online or offline (locally). The online face searching is most commonly known as “people search” or “reverse image search” or “similar image searching”.

Sightcorp state-of-the-art face search

Currently, there are many face recognition search services available in the market. Interestingly, most are machine learning and not deep learning-based.
We offer a state-of-the-art face searching model which is 100% deep learning-based and built by our team of experts in computer vision.

If you want to know more or get a demo, please contact us through any of the forms.

How does face search work?

The most known and popular applications of face search are Celebrity face search tools and “Find your doppelganger” apps. These applications allow you to upload a picture of yourself or another person and then run a search online or in another publicly available dataset.

What this application also does is to perform online face-matching tasks and also perform the interesting task of matching up two or more different photos. Our face matching technology uses facial recognition technology to search image databases that are either our own or from our customer.

What you can expect from a live demo with us is very straightforward as we will upload two different photos to our servers and process the results live. You can provide us with the pictures on the spot or we can use images from our datasets. After processing the results, we will show the percentage of likelihood that the two faces in the images are the same. While it is a fun tool, it can serve many important purposes as well, varying from Hospitality to KYC in banking and security.

Trusted by Leading Companies

Ready to get started with our face recognition technology?

Test it free for 2-weeks on your favorite desktop platform

Start Free trial  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.