The Sound, Image and Brain project is looking for Neurosky users to play an online game and help us gather some data for event related potential analysis. More details here: http://www.doc.gold.ac.uk/eavi/EAVI/?page_id=171
I just published a short video that shows how a cheap contact microphone can be used to recognize different types of fingers touch and transform any surface into an interactive board. Users can train the software with their own ‘gestures’, using both bare hands and objects. In the video demo we put the microphone over different surfaces such as kitchen tables and balloons. The sound synthesis is based on two different techniques:
1 - physical modeling, which consists in generating the sound by simulating physical laws. Different materials can be simulated, such as membranes, strings, tubes and plates
2 – mosaicing, that works as follow: first, users load a sound folder; then, the noise coming from the microphone is analysed and the software continuously finds and plays its closest segment within the sound folder.
More details: www.brunozamborlin.com/mogees
I’ve been working on modeling facial expressions and head-pose, and recently came across two very good libraries. One, Jason Mora Saragih’s work on shape modeling , and a library by GreatYao, aam-library.
Here I am using Jason’s library for automatically building a database of images with 67 facial landmarks tagged in each of them.
After 200 images of training, I use aam-library to build an active appearance model and register my own face with a reprojection. The results are pretty fun:
Last week we visited IRCAM (Institute de Recherche et Coordination Acoustique/Musique) in Paris, where Bruno Zamborlin is working before joining us for his PhD. In particular we met with Fréderic Bevilacqua, leader of the Real-time Interaction Group. They are doing a lot of exciting work around gesture and movement. We have agreed to collaborate in future, around Bruno’s PhD and other projects.