Comments:
Sam
Summary:
Scratch Input is an acoustic-based gesture recognizer. It uses a modified stethoscope with a single microphone embedded into it in order to capture the propagation of sound waves through a solid, flat surface. Scratches have a high frequency, and thus frequency thresholds are employed to eliminate almost all noise from the system. Gestures are distinguished mainly by the number of amplitude peaks in their signal. People slow down when approaching corners in a drawing, and thus the lowest points in a signal correspond to "corners" in a gesture. Strokes can thus be segmented as the peaks between these corners. The single input sensor used was unable to differentiate between gestures that contain the same number of strokes, but has an accuracy of 90% for the gestures tested. The hardware device designed by authors was extremely affordable, thus allowing for Scratch Input to be applied to a variety of large surfaces as needed by potential users.
Discussion:
Good ol' scratch input! Our Sound Board project was based heavily off of the ideas in this paper. I would love to see the authors return to this work and employ multiple sensors. That would essentially do what Drew, George, and I tried to do with our 3rd and Final projects.
I really liked your idea of using multiple sensors. I think this may overcome the problem of lacking spatial location. It is very hard to make recognition without explicit spatial information. We had similar problems with the wii.
ReplyDeleteYour project yesterday was awesome. This paper motivated us working on sound project. Perhaps i can use your idea in my sound project in the future by using multiple sensors.
ReplyDeleteUsing multiple microphones is really good to recognize gestures. I also suggest using some multisensor fusion techniques to deal with information from multiple sensors. The problem is that with multiple microphones, it seems not easy to incorporate them into a mobile phone or other small devices.
ReplyDelete