Coming soon…
Due to the end of this year’s Google Summer of Code 2012 is approaching soon, the development of hand gesture detection plugin for Gstreamer is also going to be packed. As one of important outputs of this project, herewith I forecast the good results of natural hand gesture detection using openCV HAAR training classifiers, mainly including the gestures of fist and closed palm.
Relevant posts regarding to this project, for example, how the call for hand gesture pictures was passively responded and how the classifier was going when insufficient samples were provided, will be published shortly in a series. Topics will cover:
1. Analysis of openCV’s face detection – the sample, method and performance
2. Collection of own hand gesture samples – the call for pictures, training method, tool and results
3. First trial of classifier training – the good and bad
4. Improved classifier training – the changes and lessens learned
5. Dead try – the keys to successful classifier training (samples and parameters)