Deep Fisher Discriminant Learning for Mobile Hand Gesture Recognition

12 Jul 2017  ·  Chunyu Xie, Ce Li, Baochang Zhang, Chen Chen, Jungong Han ·

Gesture recognition is a challenging problem in the field of biometrics. In this paper, we integrate Fisher criterion into Bidirectional Long-Short Term Memory (BLSTM) network and Bidirectional Gated Recurrent Unit (BGRU),thus leading to two new deep models termed as F-BLSTM and F-BGRU. BothFisher discriminative deep models can effectively classify the gesture based on analyzing the acceleration and angular velocity data of the human gestures. Moreover, we collect a large Mobile Gesture Database (MGD) based on the accelerations and angular velocities containing 5547 sequences of 12 gestures. Extensive experiments are conducted to validate the superior performance of the proposed networks as compared to the state-of-the-art BLSTM and BGRU on MGD database and two benchmark databases (i.e. BUAA mobile gesture and SmartWatch gesture).

PDF Abstract


  Add Datasets introduced or used in this paper

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Hand Gesture Recognition BUAA F-BGRU Accuracy 99.25 # 1
Hand Gesture Recognition MGB F-BLSTM Accuracy 98.04 # 1
Hand Gesture Recognition SmartWatch F-BGRU Accuracy 97.4 # 1


No methods listed for this paper. Add relevant methods here