Image of the 'Kairos Human Analytics' logo and 'IBM Watson Ecosystem Partnership' logo


As an IBM Watson Ecosystem Partner we work with IBM Watson™ to transform how businesses understand people through unique human analytics. Kairos’ face analysis algorithms are able to recognize and understand how people feel in video, photos and the real-world. Watson is a cognitive computing platform that uses machine learning to reveal insights from large amounts of unstructured data.

Continue Reading

A young, smiling brunette woman with the words 'Project Look by Kairos' overlaid.


Project Look is a market research tool that uses best-in-class emotion detection algorithms to measure people's reactions to video content. Within minutes you can be testing your videos with your audience and get real-time, actionable insights. All in the cloud. No coding required.

Why we created Project Look

Imagining how to use a technology like face analysis is often the easy part. Applying it in the real world - that’s a whole different ball game.

Yet, this is what motivates us over at Kairos HQ. We love seeing our customers solve real business problems by using the tools we have designed. But when we spoke to early customers, we realized these tools weren’t the only part of their journey.

Continue Reading

A line graph and text describing emotions overlayed on the face of an attractive, brunette young woman who looks surprised.


People used to think the earth was flat. That theory was disproved by many famous mathematicians, but before those discoveries, humans perceived the universe in two dimensions. Fast forward to today, while the earth is still round, business, an integral part of modern-day society, is still only running on engines of two dimensional data.

Continue Reading

An array of colored speech bubbles overlapped one another


The research of facial recognition has been a fascinating journey. It began in the 1960s with Woody Bledsoe, Helen Chan Wolf, and Charles Bisson who created programs to assist with basic face recognition. They were not fully automated back then, requiring the administrator to locate the key facial features such as the eyes, ears, nose, and mouth on the image being examined. The programs calculated distances and ratios to a common reference point which was then compared to set reference data.

Since those early days, many facial recognition research groups have examined various aspects of facial detections and recognition. By the 1970s Goldstein, Harmon, and Lesk were able to automate the recognition process by using 21 specific subjective markers, such as hair color and lip thickness.

Kirby and Sirovich's research in the late 1980s gave another leap forward to the nascent technology, by determining that less than one hundred values were required to accurately code a suitable aligned and normalized face.

I have found 56 locations where facial recognition research groups have been the vanguard of 21st-century research into facial analysis. Some of this research is now historic, although still freely available on the internet. In other cases, the research is ongoing, with capabilities and techniques being improved on all the time. Some of the research is very clearly focused on facial research. Some of the other studies have only a peripheral connection to the subject.

I have tried to include all facial recognition research groups whose work appears on the internet. If you know of a group that is missing from this article feel free to contact us at Kairos and I am happy to update this post.

Continue Reading

Who's talking about facial recognition privacy?


The biggest news in the facial recognition industry this month has been the walkout from the ongoing facial recognition privacy talks by the nine consumer/privacy representatives. While the media has widely reported the walkout, as in this New York Times article, often quoting from the privacy advocates' press statements, there has been little public comment from members of the facial recognition industry. As a strong supporter of these talks, we at Kairos would like to share our viewpoint.

Continue Reading

Get meaningful data. Make smarter decisions.