Sightcorp logo

Face Detection

Everything about Face Detection


What is Face Detection?

Face detection is a computer technology that is being applied for many different applications that require the identification of human faces in digital images or video. It can be regarded as a specific case of object-class detection, where the task is to find the locations and sizes of all objects in an image that belong to a given class. The technology is able to detect frontal or near-frontal faces in a photo, regardless of orientation, lighting conditions or skin color.

How does Face Detection work?

Face detection applications use algorithms that determine whether images are positive images (i.e. images that include a face) or negative images (i.e. non-face images). To be able to do this accurately, the algorithms must be trained on huge datasets containing hundreds of thousands of face images and non-face images.

Once trained, the algorithms are able to answer two questions in response to
input in the form of an image:

  • Are there any faces in this image?
  • If yes, where are they?

If a face or faces are present in an image, the algorithms will answer these questions by placing a bounding box around the detected face(s), as illustrated below:

Face detection - sightcorp

In the past, these algorithms were machine-learning based, and were heavily affected by factors such as extreme head poses (where the head is rotated far to one side or tilted far up or far down, for example) and varying lighting conditions. Today, however, we can use deep learning methods to carry out accurate face detection in a wide range of scenarios.

Read: Detect Faces with Increased Accuracy: Benchmarking Sightcorp’s New Deep Learning-Based Face Detector

Why is Face Detection important?

Face detection is the first step in various other applications, including face analysis and face recognition.

In the context of face analysis, face detection tells the face analysis algorithms which parts of an image (or video) to focus on when identifying
age, recognizing gender, and analyzing emotions based on facial expressions.
And when it comes to facial recognition, face detection is necessary for the algorithms to know which parts of an image (or video) to use to generate the faceprints that are compared with previously stored faceprints to establish whether or not there is a match.

How can you use Face Detection?

Aside from using face detection in conjunction with the technologies described above, you can use face detection to:

  • Count the number of people entering a retail store or looking at a digital display
  • Identify which areas of an image to blur to ensure privacy (see Face Blur)


Discover products that have face detection

Below are other articles that you might find interesting:


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.