FINGeR: Framework for Interactive Neural-based Gesture Recognition

For operating in real world scenarios, the recognition of human gestures must be adaptive, robust and fast. Despite the prominent use of Kinect-like range sensors for demanding visual tasks involving motion, it still remains unclear how to process depth information for efficiently extrapolating the dynamics of hand gestures. We propose a learning framework based on neural evidence for processing visual information. We first segment and extract spatiotemporal hand properties from RGB-D videos. Shape and motion features are then processed by two parallel streams of hierarchical self-organizing maps and subsequently combined for a more robust representation. We provide experimental results to show how multicue integration increases recognition rates over a single-cue approach.

@InProceedings{PBW14,
 	 author =  {Parisi, German I. and Barros, Pablo and Wermter, Stefan},
 	 title = {FINGeR: Framework for Interactive Neural-based Gesture Recognition},
 	 booktitle = {European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN '14)},
 	 journal = {None},
 	 editors = {}
 	 number = {}
 	 volume = {}
 	 pages = {443--447},
 	 year = {2014},
 	 month = {Apr},
 	 publisher = {None},
 	 doi = {}
 }