YOUR QUESTIONS ANSWERED
Starting with Kairos
What is Kairos?
Kairos provides state-of-the-art, ethical face recognition to developers and businesses worldwide. Through computer vision and deep learning, we recognize faces in videos, photos, and the real-world—our innovative API platform simplifies how you integrate human identity into software products. Founded in 2012, we’re headquartered in Miami with offices in Singapore. We’re a venture backed organization with customers all over the world.—Learn more about Kairos.
How do I use Kairos?
Kairos is designed for software developers and we’ve made it simple to interact with our technology via an API (ask your tech team). Just integrate with our easy to code endpoints to get up and running. Alternatively, you can install a version of Kairos on your own servers!—Ways to buy Kairos.
What features does Kairos offer?
We’re deeply focused on all facets of face recognition—See core features.
How accurate is Kairos face recognition?
Kairos is state-of-the-art—scoring 99.63% on the popular LFW database. That said, accuracy of individual results really relies upon the quality of submitted images/video and the settings customers choose through our API. Like any technology, the more controlled the environment, the better the results. Yet even in less than optimal conditions such as uneven lighting or side poses— our algorithms can compensate. Cool, right?! And, if you find you’re not getting the outcomes you expect, we can work with you to improve your results—Learn more about Best Practices for Face Recognition.
How does Kairos compare to other face recognition providers?
This guide shows how we fare against the competition—we think you’ll be impressed. Unlike many in our industry, we’re outspoken about the misuse of face recognition technology by law enforcement agencies and governments.
Do you have a Demo?
We do—Try our face rec demos.
Can you provide case studies?
We can. All kinds of businesses use Kairos to add face recognition into their products. In fact, we’re trusted by global media agencies, innovative start-ups, and some of the world’s largest organizations. Our customers process millions of faces each month thru our API platform—See how customers use Kairos.
Can I use Kairos for people counting?
Sometimes. While face recognition isn’t really designed for people counting, you can still use it to get a sense of how many people come in and out of frame. For example: careful consideration of your camera positioning could ensure you get as many people’s faces as possible— Learn more about Best Practices for Face Recognition.
Is there a limit to how many faces can be stored in a gallery?
No, but it also depends on your need. Our largest customers store and process many millions of faces each month—and you can, too.
What are ‘face templates’?
Each time you enroll a face into the API, it extracts the facial features, generating a template of the features as a random alphanumeric string of code. This anonymizes the facial data therein and the template cannot be reverse engineered back into a photo. When you compare faces in our system, you are actually comparing templates. So, each enrolled face counts as 1 template.
Pricing & Billing
How much does it cost to use Kairos?
We offer straightforward pricing that compliments your usage needs and business goals.
Our Cloud API subscription plans all start with a free trial* and then you’re billed a flat rate based on your usage needs, plus a small per-transaction fee.
Our On-Premises/Self-hosted solution is priced a little differently. You would purchase a license or licenses, tailored for your usage needs—See our pricing guide.
How am I billed?
That’s easy. When subscribing to a Cloud API plan, you will be charged monthly on the 1st of every month and pro-rated for your first month.
If you signed up on August 5, and complete your free trial period, you would get a bill on August 19 for the pro-rated days remaining in August; on September 1st you would get a bill for the month of September PLUS your per transaction usage fees for August.
You will receive an email notification about your successful payment along with the invoice, all accessible in your dashboard too.
For On-Premises licenses, we offer custom billing options to best fit your needs—Contact us to learn more.
What sort of support do you offer?
We offer two flavors of support:
Standard (Free for all): Office hours* email & online Documentation.
Premium (Monthly fee; Enterprise plans only): 24/7 dedicated tech engineer & guaranteed priority response.
*Standard Support office hours: Mon-Fri, 9-5PM US Eastern Time excluding major US holidays.
Security & Privacy
Is Kairos Face Recognition secure?
Yes. High level encryption and tokenization of sensitive data are standard practices at Kairos. Kairos' system is hosted at Amazon Web Services (AWS) and Google Cloud Platform (GCP). Kairos offers 2048 bit SSL encryption for all data in transit and AES-128 XTS encryption at rest for customers’ face templates and AES-256 for all backups and image storage. All of the transactions you submit to our API is through a user-generated key. The key you generate authorizes the engine to perform tasks on your behalf.
Payments are processed through our partner Braintree. We never see your credit card details.
Is my information private?
Yes it is. We do not use any personally identifiable information, and any face template data we create cannot be reverse engineered. Your image classification in the API only needs to make sense to you. This means you can use anonymous or tokenized identifiers instead of personal data such as employee numbers. For added peace of mind we highly-recommend our On-Premises edition, giving you ultimate control over your data and networks.
What encryption do you use?
If you use our HTTPS API your data is encrypted in transit with 2048 bit SSL. We use encrypted storage volumes, and our backups are encrypted as well.
Where is my data stored?
At Amazon Web Services (AWS) and/or Google Cloud Platform’s (GCP) secure cloud— which is housed at multiple locations throughout the United States. If your company is located outside the US and you wish to host your data at your native country, you can. We’re able to host our infrastructure at other locations throughout the world such as Brazil, Germany, Ireland, Singapore, etc.—Contact us to learn more.
For applications that require a higher level of security that cannot be provided in a multi-tenant installation such as the Cloud API, the On-Premises product is recommended so customers can ensure their data never leaves their four walls.
Can I delete my data?
Do you sell your technology to government and/or law-enforcement organizations for surveillance programs?
Using Kairos' API
How does the Kairos Face Recognition work?
1. You submit images or video-frames into our API.
2. We find all the faces and return detailed facial information back in the form of code objects (JSON). These results include feature points, age, gender, ethnicity, and a ton of other useful data about the human face—See all features.
You can also create galleries of faces from your images and videos to be used later for face verification or identification (‘face recognition’). All of the transactions you submit is through a user-generated API key. The API key you generate authorizes the engine to perform tasks on your behalf.
PRO TIP: Wanna do Face Rec in a video stream?
You’re going to need to pull frames from the video and send it to the API endpoints. There are different ways to pull frames from video, we recommend using FFMPEG. Below is an example video that we put together showcasing how you pull frames out of a video using FFMPEG—See how to split video into frames using FFMPEG
What counts as an API transaction/call?
An API 'call’ or 'transaction' is an HTTP request sent across the Internet to our API. E.g., A ‘call’ would be enrolling a face into a gallery to later be recognized, or a photo sent to us with the request that the faces in it be detected. Requests to view galleries, remove faces, list galleries, are also considered a ‘call’.
Do you have an on-premises or self-hosted solution?
How fast is the Kairos API?
Fast. We typically match faces or enroll images in under a second. This speed can be affected by the size of the image, the number of faces in the image, and your use case. We’ve found that low resolution images work just as well as high resolution images as long as there are at least 75 pixels between the person’s eyes. The smaller the image, the faster it is able to be processed. We can process images as small as 12 KB with great success.
For example, when you submit images we automatically compress them, rotate and convert them to grayscale in order to speed up the process and save you bandwidth. We do offer an offline version, which is faster because it doesn't need to send data across the Internet. However, we do recommend customers use the Cloud API to create their proof-of-concepts—Test for free before you scale.
What files does the Kairos API support?
Image files can be BMP, JPG, or PNG. We currently do not support GIF.
What are ‘thresholds’, and how do they affect face recognition accuracy?
When a face is matched against all the enrolled faces in your gallery, Kairos returns a confidence score between 0 and 1. The higher the number, the more confident the system is about the match. Depending on your needs, you can set a threshold number between 0 and 1, and any value above your chosen threshold would be considered a match, and any value below that threshold would be considered a no match. For example, if you set your threshold at .82, any match with a score that is equal to or greater than .82 would be considered a match—Learn more about using thresholds
How does ‘quality’ score work?
The quality score indicates how reliable the image will be for future matching. For example, if the image is blurry, has small number of pixels between the eyes, out of focus, etc. the quality score will be low (0 or less than 0) and it would not be good to match against.
What types of cameras work with the Kairos API?
All kinds. We test our API on images and video-frames captured from a multitude of devices. From embedded smartphone cameras to webcams to DSLRs—we get equally good results from both ends of the spectrum.
The accuracy of your results relies upon the quality of your enrollment and recognition photos. It works best when there are at least 75 pixels between the person’s eyes—Learn more about Best Practices for Face Recognition.
Do you offer a Mobile Face Recognition SDK?
We don’t currently offer a native solution for mobile (i.e on-device SDK). However, for a mobile use case, you can still use cloud and/or on-premises API to achieve a reasonable outcome, depending on your requirements—Connect with our team and we'll show you how.