July 19, 2017

Gender Age Emotion Ethnicity Recognition

Gender Age Emotion Ethnicity Recognition

While Face Augmented Reality creates emotional experiences, how about measuring the audience’s engagement on .. people’s faces? Clicks lie. Face don’t (unless you play Poker 😉

We are conducting research & development on all of the above domains with an Academic Research partnership.

Watch the Gender & Age detection, fresh from the Labs. The R&D phase is complete.

We are currently engineering this software into a top performance mobile SDK.

Emotion recognition

Emotion recognition is the process of identifying human emotion from facial expressions automatically using computational methodologies.

Gender Age & Ethnicity Recognition

Gender Age & Ethnicity recognition from face images is an important application in the fields of retail advertising, marketing and security. MoodMe SDK is based on specialized filters for gender age & ethnicity recognition respectively. MoodMe filters are trainable, in that its selectivity is determined in an automatic configuration process that analyses a given prototype pattern of interest. MoodMe SDK has demonstrated the effectiveness of the approach on its own datasets with 760 training samples and achieved accuracies above 87%.

MoodMe Gender Age Ethnicity Emotion SDKs are being developed under collaborative research with AIT. Watch the team of Computer Vision researchers analyzed by their own algorithms.

These outperform approaches that rely on classifiers. Automatic gender age & sometimes ethnicity classification has become relevant to a broad range of applications. Nevertheless, performance of real-world images methods was lacking compared to the leaps in performance in face recognition. The use of neural networks delivered a significant increase in performance.