TY - CHAP
T1 - Learning fast hand pose recognition
AU - Krupka, Eyal
AU - Vinnikov, Alon
AU - Klein, Ben
AU - Bar-Hillel, Aharon
AU - Freedman, Daniel
AU - Stachniak, Simon
AU - Keskin, Cem
N1 - Publisher Copyright:
© Springer International Publishing Switzerland 2014.
PY - 2014/1/1
Y1 - 2014/1/1
N2 - Practical real-time hand pose recognition requires a classifier of high accuracy, running in a few millisecond speed. We present a novel classifier architecture, the Discriminative Ferns Ensemble (DFE), for addressing this challenge. The classifier architecture optimizes both classification speed and accuracy when a large training set is available. Speed is obtained using simple binary features and direct indexing into a set of tables, and accuracy by using a large capacity model and careful discriminative optimization. The proposed framework is applied to the problem of hand pose recognition in depth and infrared images, using a very large training set. Both the accuracy and the classification time obtained are considerably superior to relevant competing methods, allowing one to reach accuracy targets with runtime orders of magnitude faster than the competition. We show empirically that using DFE, we can significantly reduce classification time by increasing training sample size for a fixed target accuracy. Finally, scalability to a large number of classes is tested using a synthetically generated data set of 81 classes.
AB - Practical real-time hand pose recognition requires a classifier of high accuracy, running in a few millisecond speed. We present a novel classifier architecture, the Discriminative Ferns Ensemble (DFE), for addressing this challenge. The classifier architecture optimizes both classification speed and accuracy when a large training set is available. Speed is obtained using simple binary features and direct indexing into a set of tables, and accuracy by using a large capacity model and careful discriminative optimization. The proposed framework is applied to the problem of hand pose recognition in depth and infrared images, using a very large training set. Both the accuracy and the classification time obtained are considerably superior to relevant competing methods, allowing one to reach accuracy targets with runtime orders of magnitude faster than the competition. We show empirically that using DFE, we can significantly reduce classification time by increasing training sample size for a fixed target accuracy. Finally, scalability to a large number of classes is tested using a synthetically generated data set of 81 classes.
UR - http://www.scopus.com/inward/record.url?scp=84984918434&partnerID=8YFLogxK
U2 - 10.1007/978-3-319-08651-4_13
DO - 10.1007/978-3-319-08651-4_13
M3 - Chapter
AN - SCOPUS:84984918434
T3 - Advances in Computer Vision and Pattern Recognition
SP - 267
EP - 287
BT - Advances in Computer Vision and Pattern Recognition
PB - Springer-Verlag London Ltd
ER -