Subscribe
Share
blog post background
Strategy

How much does it cost to create a facial recognition system?

By Nadejda Alkhaldi, Innovation Analyst
Published on

In Portland, Maine, a man, now 86 years old, used his dead brother’s identity to collect social benefits as himself and as his brother. This case of Social Security fraud and identity theft lasted for decades until a modern facial recognition system was installed. It matched the man’s face to two different identities, ending his Social Security double dipping.

This real-life story, and many others, encourage businesses to benefit from AI services and deploy facial recognition systems. The global facial recognition market was evaluated at $5,037 million in 2022 and is expected to reach $16,380 million by 2031, growing at a CAGR of 14%.

However, the costs of facial recognition software are hard to estimate. There are hidden expenses that companies tend to overlook and, as a result, surpass the allocated budget. This article breaks down the factors influencing the total price and gives tips on reducing expenditure.

So, how much does a facial recognition system cost?

TABLE OF CONTENTS
Contact ITRex
Contact us

What is a facial recognition system, and how does it work?

Facial recognition systems are considered the most reliable among biometric identification forms, such as fingerprints and iris recognition. But the technology has its challenges. The facial recognition process often occurs in an uncontrolled environment with variable lighting conditions and dynamic backgrounds. Other factors affecting recognition quality include facial expressions, a person’s age, and ethnicity.

A facial recognition system has five main components:

  1. Hardware, which includes servers and devices responsible for capturing images

  2. Connectivity technology allows hardware devices to transmit images for further analysis, either to the cloud or to other devices on premises

  3. Facial recognition software is a biometric tool that extracts faces from images and matches them to the existing database of faces for identification

  4. Database of faces is a collection of identities, such as an employee database or a hub for social media images

  5. Client-side web/mobile app is an interface that enables users to view the results

Here is how facial recognition systems work:

cost of facial recognition software

After detecting a face, facial recognition software reads the facial geometry, which encompasses around 80 different elements. The key features include the distance between the eyes, eye socket depth, cheekbone shape, and jawline length. When the analysis is complete, the tool will generate a facial signature as a mathematical formula and compare it against other faces in the repository.

According to recent studies, facial recognition systems are reasonably accurate. For instance, the US National Institute of Standards and Technology achieved an accuracy rate of 99.88% with the Idemia facial recognition algorithm.

Facial recognition systems have many exciting applications in different industries. One simple example of this technology is photo tagging in Google Photos, where the tech giant compares faces in one image to a preexisting database of uploaded photos to identify users.

Which factors influence facial recognition systems’ price?

Let’s explore the four key factors.

1. Hardware

Companies need to carefully consider their hardware choices to avoid getting their hopes high with a software solution that their devices can’t handle. But at the same time, firms shouldn’t overpay for computational resources that they will not use. To have a working facial recognition system, you will need to procure cameras, switches, and servers for data storage and processing (unless you’re planning to use the cloud). All these utilities will add up to your facial recognition system’s price.

Camera options

The camera type and its location depend on the desired coverage, image quality, and angle of view. For example, if the device needs to capture a person standing one meter away, a 3-8mm lens camera is recommended. Examine the location where you want to install cameras. In the case of poor lighting conditions, opt for devices with built-in features that can compensate for the lack of light and still produce images that your facial recognition software can work with. Also, some facial recognition algorithms require 3D cameras.

You might consider purchasing cameras that come with pre-installed computer vision software and can accomplish tasks like pre-processing and face detection. This arrangement will take some load off your custom facial recognition software, increasing its speed. Such cameras can easily exceed $100 per device. Here is an example of what such gadgets can do:

Hardware configuration

There is no standard hardware configuration suitable for every facial recognition task. So, organizations need to consider their requirements carefully. If the chosen format is not powerful enough, it will cause delays and quality degradation.

Let’s assume the task at hand is to identify a person posing in front of a camera. To achieve this, we need two neural network models—a face detector and a face recognizer. We have to process at least six frames per second. Higher frame rates offer more accurate and realistic depictions. With these requirements, one could make do with a low-cost graphics processing unit (GPU), and even a central processing unit (CPU) might suffice. However, if we complicate this task by tracking people’s trajectories and actions or even increasing the number of cameras, we will have to procure a more powerful and expensive GPU.

2. Facial recognition software

Different types of ready-made facial recognition software are available on the market. These tools vary in their features and pricing models. Here are a few examples to help you gauge how much off-the-shelf facial recognition software costs:

Features Facial recognition software pricing model Free plans/trials
Amazon Recognition
  • Compares faces in different images and videos

  • Detects and analyzes faces and emotions (happy, sad, male, female, etc.)

  • Detects protective equipment, such as facial masks, helmets, etc.

  • Identifies well-known people

  • Identifies faces for the purpose of authentication

In addition to face-related work, Recognition can also detect and label text and other objects and perform content moderation.

Amazon charges clients each time they use one of its APIs. So, processing one image through two APIs will double the costs.
After the free tier expires, the total costs will be calculated based on the number of images processed and the classifiers used.
The price starts at $0.001/image for the first 1 million images.

Free tier for 12 months. Clients can analyze 5,000 images/month and store 1,000 face metadata objects.

Microsoft Face API
  • Detects one or several faces in a photo

  • Identifies people based on a repository of photo IDs

  • Detects attributes, such as facial masks and glasses

Microsoft offers a pay-as-you-go model where users can pay $1 per 1,000 transactions if they choose to do less than a million transactions. And the payment per 1,000 transactions decreases as users opt to execute more transactions per month. There is also a separate charge for face storage.

You can do 30,000 transactions/month for free at a rate of no more than 20 transactions per minute.

Face++
  • Detects human faces in images

  • Compares faces in different photos and determines if they belong to the same person

  • Finds similar-looking faces and generates a confidence score for similarity

  • Merges faces from different images

In addition to detecting faces, this tool can identify and outline human bodies.

You can choose your own pricing model. You can pay daily, monthly, or per use.
The price depends on the classifier type. Facial Recognition classifier is the cheapest. Such a face recognition model will cost you $100/queries per second (QPS)/day or $1,000/QPS/month.
Skin Analyze and Dense Facial Landmark classifiers are more expensive and will cost you $500/QPS/day or $10,500/QPS/month.

You can try the services for free. One account will be assigned one free API key. You will have a limitation of 3 QPS for regular facial recognition and 1 QPS for the Dense Facial Landmarks API.

Kairos
  • Detects multiple faces in photos

  • Recognizes faces and verifies identities

  • Detects demographic features, such as age, gender, and race

  • Includes anti-spoof security features

Kairos offers several payment plans based on the functionality and the number of transactions per minute. The costs of this facial recognition app range from $19/month + $0.02/transaction to $499/month + $0.001/transaction. There is also the possibility of arranging for a custom plan.

There is a free trial.

Sky Biometry
  • Detects multiple faces at various angles

  • Identifies faces and determines demographics, such as age and gender

  • Discovers attributes, such as glasses, and detects if a person is smiling

In addition to the free plan, there are three paid plans: €50/month, €100/month, and a custom plan. Each plan has its own restrictions on the number of transactions. The paid plans include two business days of support. There is also the possibility of crafting a custom plan.

Sky Biometry offers a free-of-charge plan, allowing users to make 100 transactions/hour with a maximum of 5,000 transactions/month. Other restrictions apply.

You can see that different vendors offer variable pricing arrangements, allowing clients to select the suitable model based on the number of transactions planned per month, the speed of image processing, and the classifiers used.

It is crucial to note that face recognition software costs cited above account for subscription fees only, which are just a part of the overall expenses. Facial recognition solution vendors allow client companies to use their APIs, but you still need to integrate them into your system. You can turn to custom software vendors to facilitate integration and build a client-side application, which allows you to reap the full benefits of the facial recognition software. For example, integrating a third-party facial recognition tool that only does face detection and identification will cost you around $7,800, and this number will increase with the scope of the facial recognition solution.

You might also require additional features, such as enhanced security or on-premises storage, for sensitive applications where you can’t risk transmitting your data to the vendor’s cloud system. Computer vision development companies can help you build additional layers of functionality to supplement ready-made facial recognition solutions. For example, as part of a large project, we developed a microservice for anti-spoofing as middleware between the client-side application and the facial recognition software API. Such microservices cost around $10,000–$15,000, including development, training, and deployment expenses.

So, your final facial recognition software costs will accumulate everything mentioned above. Looking solely at software vendors’ licensing prices can be misleading.

Ready-made solutions are an excellent choice when you want to launch your product quickly and avoid spending on infrastructure. If you want a solution with specialized requirements, think of a facial recognition system at a hospital where some people wear a mask and some don’t. Then it is best to invest resources into building and training a custom facial recognition tool.

3. Connectivity requirements

If a company operates from a remote location where different communicating objects are positioned far apart, you will need to establish a reliable communication channel. Such high-quality cables can be even more expensive than servers and cameras and will account for a large portion of the total costs of a facial recognition system.

We can reduce connection bandwidth requirements by installing the server responsible for video pre-processing close to the cameras and using proximity detection to avoid transmitting around the clock. We can also use Edge AI. In this case, the server will analyze the stream, extract images of interest, and transmit them further to the main server instead of streaming the entire video. This configuration can operate on 1-2 Mbit per second, even with multiple cameras, if there are no strict requirements on responsiveness and stability.

4. The complexity of your facial recognition solution

Logically, the more features you want to include, the higher the price. Some off-the-shelf solutions, such as Face++, set their prices based on the classifiers used, with more complex classifiers being more expensive.

The same applies to custom facial recognition solutions. The system may include classifiers, such as face detection, face verification, face grouping, similar face search, etc. The more models you accumulate, the more the final solution will cost. But the number of classifiers is only one of several attributes impacting complexity. Other parameters include the solution’s scalability, number of images being processed, security requirements, availability, and fault tolerance.

A simple solution that merely counts the number of faces in a picture will take one or two days to build and train. The costs of developing this type of face recognition app are $650–1,300, while more complex facial recognition tools can cost tens and even hundreds of thousands.

Here is one example of a rather complex facial recognition system. An enterprise risk management company based in the US reached out to ITRex to develop a comprehensive biometric-powered cybersecurity solution to identify people based on their unique facial features. Our team opted for Microsoft Face API to deliver a solution with a diverse set of functions. We built a system that relied exclusively on biometric parameters as cyber credentials. It offered secure data transfer and storage space, a person-to-person live video interaction channel, and had its own proprietary cybersecurity protocol that can be used by third-party software. This system could also operate in high-load cloud environments and included microservices that enabled painless scaling and change implementation.

The costs associated with such a facial recognition solution could easily surpass $500,000.

How to minimize facial recognition system costs in the long run?

System complexity directly influences the cost of facial recognition software. You can deploy a doorbell camera bundled with an associated cloud solution and a white label mobile app for a few thousand dollars. While a highly complex and secure solution will cost you up to $500,000 or even more. The location of operations also influences the total price. If you need to survey large warehouses with hundreds of cameras, hardware costs will form a large part of your expenditures.

But even with complex solutions, you can plan ahead to ensure the allocated budget is wisely spent. Don’t make the mistake of opting for a cheaper tool only to end up spending more on security fines than you saved on the software itself. And those fines can be rather hefty. Not long ago, the UK’s Information Commissioner’s Office (ICO) charged a prominent American facial recognition company, Clearview AI, with £17 million in penalties as it failed to obtain consent when gathering publicly available photos of British citizens and using them in training datasets.

Here are a few tips that will help you make cost-effective decisions:

  • Opt for a ready-made solution if you have standard requirements and want something to be up and running in a matter of days without spending a lot on infrastructure. However, if you have unique and complex requirements, then it is best to invest in a custom facial recognition solution.

  • Invest in your system’s security. If your favorite ready-made solution doesn’t offer any reliable options, you can hire a custom software development vendor to build an anti-spoofing middleware and additional security features. Also, make sure you are familiar with the data protection laws in the countries of your operation.

  • If you decide to provide a training dataset yourself or compose it with your vendor, work on eliminating bias. Many open-source datasets are skewed towards the white male population. So, make sure the data you use is a faithful representation of your target population.

  • Don’t procure hardware with barely enough power and storage capacity to cover your current needs. Leave a margin for estimation errors and possible business expansion. Also, as you update your facial recognition software, it might become more demanding.

To sum up, the amount of money necessary for facial recognition software depends on multiple factors. And if you can take all of them into account, you will have a more realistic idea of what you can get with your budget. Don’t limit yourself to what is available on the market. If you have rather unique requirements, turn to custom software developers for tailored solutions.

TABLE OF CONTENTS
What is a facial recognition system, and how does it work?Which factors influence facial recognition systems’ price?1. Hardware2. Facial recognition software3. Connectivity requirements4. The complexity of your facial recognition solutionHow to minimize facial recognition system costs in the long run?
Contact ITRex
Contact us
background banner
background banner

Thinking about deploying a facial recognition system? Get in touch! Our computer vision experts will help you integrate with the selected vendor’s API, build client-side software, and even develop a custom facial recognition application if needed.