At Affectiva, our mission is to humanize technology. Using our software development kit (SDK) you can be part of this! Enrich digital experiences. Add emotion awareness to apps, games and other products. Allow devices to respond to users’ emotions in real time. This is Emotion AI.
Use our SDK to detect emotion in real time on device to analyze your recorded media in the cloud. We support 8 platforms including iOS, Android, Web, Windows, Linux, macOS, Unity and Raspberry Pi. We identify 7 emotions, 20 expressions and 13 emojis and include classifiers for age, gender and ethnicity. The SDK detects emotion on individual faces as well as for groups of 20+. Best of all, our solutions takes just a few hours to setup, giving you the ability to fully emotional enable your applications – in an afternoon!
In addition to our general Emotion SDK, we have also developed Affectiva Automotive AI, our automotive SDK. This solution provides a subset of facial and vocal emotion and cognitive state metrics that are relevant for automotive use cases, and have been tested and trained on large amounts of real-world driver and passenger data. Learn more about Affectiva Automotive AI here.
How it Works
The Emotion SDK is designed to analyze spontaneous facial expressions that people show in their daily interactions. Our technology works with any optical sensor, device camera or standard webcam. Computer vision algorithms identify key landmarks on the face – for example the corners of your eyebrows, the tip of your nose, the corners of your mouth. Machine learning algorithms (classifiers) then analyze pixels in those regions to classify facial expressions. We use Facial Action Coding System (FACS) to classify facial expressions or Action Units (AUs). Combinations of these facial expressions are then mapped to emotions.
The SDK is built on our industry-leading patented science. The highly accurate classifiers have been trained and tested using Affectiva’s massive emotion data repository—the world’s largest emotion database with more than 6.5 million faces from 87 countries analyzed.
Designed for developer ease-of-use, the SDK processes emotion data on-device (no cloud round trip), and the library is lightweight and fast to support a small memory footprint and real-time processing.
“Leveraging the Affectiva’s SDK we were able to provide a unique way for customers to sample Hershey’s products in real time while they were making a decision at the point of purchase. No other emotion SDK has been as accurate and easy to use.” Steve McClean – President Wild Blue Technologies