Campus HagenbergInformatik, Kommunikation, Medien

Studienprojekte

Projekte sind ein essenzieller Bestandteil des Curriculums von Mobile Computing. Die Studierenden bekommen die Möglichkeit, das im Zuge ihres Studiums erworbene theoretische Wissen selbst praktisch umzusetzen. Ein sowohl für StudentInnen als auch für Lehrende immer wieder spannendes Unterrichtskonzept, in dem schon erfolgreiche Startups wie z.B. runtastic und Butleroy ihre Anfänge gefunden haben.

Finger Recognition on mobile device

Zeitraum
Mar 2015 - Jun 2015
FH Studierende
Elena Zueva
FH BetreuerIn
FH-Prof. DI Stephan Selinger

In this project I present an investigation of the finger recognition in the interaction of mobile device. The android application with the use of MYO armband recognizes thumb and index finger using accelerometer, gyroscope or EMG signals. Different methods are evaluated and compared.

Ziel

It is important to analyze how user interacts with the mobile device and how to improve interaction in more efficient way. Besides the testing and evaluation purposes, finger or gesture recognition can lead to building completely different interface on mobile device.

The goal of proposed system is to collect different data when user interacts with the device, experiment with it and find patterns in finger recognition. Current system can recognize the interaction with thumb and index finger on Android device using accelerometer and gyroscope data.

With the help of MYO armband that provides raw accelerometer, gyroscope and EMG signals it is possible to use them as an input to machine learning tools in order to make finger predictions. Different kind of input data was used to experiment: acceleration magnitudes, degree of freedom (pitch, roll, yaw) and electromyography signals. The best prediction rate in prediction of index and thumb finger was achieved with the gyroscope data.