Kepler Vision Technologies BV

“Communicating in real life a message consists of three separate elements: words (what is actually said), tone of voice (how we say the words), and body language. Research shows that of these three, the body language accounts for a whopping 55% of the overall message. In order for a human being, or for a robot, to actually understand such body language, visual recognition is required of a person’s gestures, posture, eyes, movement, touching, and appearance.

In the last few years, deep learning has led to very good performance on a variety of problems, such as visual recognition, speech recognition and natural language processing. Leveraging on the rapid growth in the amount of the annotated data and the great improvements in computer hardware, completely new and state-of-the-art results have been achieved.

Kepler Vision Technologies is a spinoff company from the University of Amsterdam specialized in developing vision-based body language understanding software, thereby opening up completely new business opportunities.”