Sightcorp logo

How to Use Face Recognition in Your Access Control System

Face recognition, whether on its own or as part of a two-factor authentication system, has quickly become a popular option for securing access-controlled environments. In this article, we will briefly explore how facial recognition works in an access control system and what the benefits are, and then we’ll look at how you can implement this technology in your own environment. How does facial recognition work in an access control environment? Process When used for access control, facial recognition software compares the face presented at the point of access to a database of authorized persons to determine whether there is a Lire la suite

What is Face Authentication and How Does it Differ from Face Identification?

Face recognition is a popular topic right now. And since it’s a relatively new topic, it makes sense that there is still some confusion regarding the related terminology. We’ve already covered the difference between face recognition and face detection in another article. Now it’s time to explore two even more closely related terms: face authentication and face identification. Let’s start by saying that face authentication and face identification are both forms of face recognition. However, there are some important differences, which we explore in this article. Face authentication: Also referred to as face verification, this term refers to the process Lire la suite

Face Recognition for Smart Home Locks – 3 Things to Look Out For

Smart locks generally don’t replace physical keys, but they do give you more control. If you equip the front door of your home with a smart lock, for example, you could: Use keyless entry to enter your home when your hands are full with groceries Check whether your door is open or closed, locked or unlocked, using an app Lock and unlock your front door from a distance Give limited-time access to friends, family, a babysitter, or someone else you want to allow into your house during a specific period   There are multiple ways to secure smart locks, and Lire la suite

Partner Integration: SmartGate

SmartGate is a managed service provider for omni-data visitor and venue insights and engagement in the retail and digital signage space. Their cloud-based solution works with their clients’ existing marketing and operations data, while also integrating with a variety of third-party data sources to create a single system of records on customer behavior and dynamic multi-channel engagement These third-party data sources include advertising networks, point of sale, video sensors that allow for face analysis, CRM plus GDPR-compliant Wi-Fi tracking that allows for counting visitors and gathering data on visitor flow within a given area. They deliver a fully managed and Lire la suite

Advantages of Using Face Recognition in Smart Home Security

With the advent of face recognition, it’s now easier than before to verify the identity of a person. Facial recognition can be applied in many fields, one being smart home security systems. With known faces captured in a database, the security cameras will identify your friends and family members and won’t give an alarm. Otherwise, you’ll get an instant alert, so you know that someone unidentified has intruded into your property. Sounds like a futuristic security option? Not anymore. What is facial recognition, and how does it work? Facial recognition is a biometric technology that goes beyond just detecting human faces in an Lire la suite

3 Ways to Super-Charge Your DOOH Advertising with AI-Powered Analytics

Digital out-of-home (DOOH) is one of the fastest-growing advertising channels available right now. And according to a report by Allied Market Research, the global value of the DOOH market is projected to reach over $8,393.30 million by 2023. This represents growth of 12.6% from 2017. Considering these statistics, it is worth examining how you can derive the most value from your own DOOH campaigns. Technology driving increased ROI in the digital signage space With the rapid technological advancements taking place, it’s becoming easier and easier to implement optimized, high-ROI DOOH campaigns. AI is one of the major forces behind these Lire la suite

On Object Detection Metrics

Anyone concerning themselves with object detection sooner or later encounters this problem: you have created your first object detector and now you want to know its performance. Sure enough, you can see the model finds all the objects in the pictures you feed it. Great! But how do you quantify that? You are familiar with precision and recall and might even have seen some precision-recall curves in the paper you just read, but how exactly do you get your model to produce those curves? And what is that magic number – “AP” – that they put in table 1? Fear Lire la suite

Partner Integration: Grassfish

Who is Grassfish, and what do they do?   Grassfish provides retailers and other customers with reliable and flexible in-store solutions to connect and interact with their customers, deliver targeted content and improve customer experience. Their digital signage solutions enable clients to display dynamic content based on the real-time demographics of their audience in the right place and at the right time. The Grassfish CMS makes controlling a digital signage network very simple. With the use of audience data, it allows users to display their content to the right people that pass by their digital signs. At the same time, Lire la suite

Announcing FaceMatch SDK – Sightcorp’s New Facial Recognition Solution

In response to increasing demand for biometric authentication technology, Sightcorp has released a new facial recognition solution, FaceMatch. There are a number of strong drivers underlying this demand: Increased demand for digital identity verification. As traditional companies become more digital and new fully digital companies arise, businesses need secure solutions to verify their users’ identities and deter fraud. Regulations including Know Your Customer (KYC) and Anti Money Laundering (AML) contribute to this demand. The introduction of the PSD2, which takes effect in the EU in September 2019 and which introduces stricter requirements for strong customer authentication (SCA). Facial recognition is Lire la suite

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

Robust face detection is at the heart of Sightcorp’s products and SDKs. Our customers deploy our technology in a variety of locations and conditions. We are expected to detect faces across different video resolutions, distances, light conditions, camera angles, and head poses. It is therefore important for us to define quantitative measures to evaluate ourselves on each of these metrics. In this post, we’d like to share how we measure performance of face detection across variations in head pose. Benchmarking our face detector in the context of head pose variation Most modern face datasets these days already include annotations with some indication Lire la suite

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.