Home > Research > Publications & Outputs > Deep Fisher Discriminant Learning for Mobile Ha...

Associated organisational unit

Electronic data

  • 1-s2.0-S0031320317305198-main

    Rights statement: This is the author’s version of a work that was accepted for publication in Pattern Recognition. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Pattern Recognition, 77, 2018 DOI: 10.1016/j.patcog.2017.12.023

    Accepted author manuscript, 3.27 MB, PDF document

    Available under license: CC BY-NC-ND: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License

Links

Text available via DOI:

View graph of relations

Deep Fisher Discriminant Learning for Mobile Hand Gesture Recognition

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published
Close
<mark>Journal publication date</mark>05/2018
<mark>Journal</mark>Pattern Recognition
Volume77
Number of pages13
Pages (from-to)276-288
Publication StatusPublished
Early online date4/01/18
<mark>Original language</mark>English

Abstract

Gesture recognition becomes a popular analytics tool for extracting the characteristics of user movement and enables numerous practical applications in the biometrics field. Despite recent advances in this technique, complex user interaction and the limited amount of data pose serious challenges to existing methods. In this paper, we present a novel approach for hand gesture recognition based on user interaction on mobile devices. We have developed two deep models by integrating Bidirectional Long-Short Term Memory (BiLSTM) network and Bidirectional Gated Recurrent Unit (BiGRU) with Fisher criterion, termed as F-BiLSTM and F-BiGRU respectively. These two Fisher discriminative models can classify user’s gesture effectively by analyzing the corresponding acceleration and angular velocity data of hand motion. In addition, we build a large Mobile Gesture Database (MGD) containing 5547 sequences of 12 gestures. With extensive experiments, we demonstrate the superior performance of the proposed method compared to the state-of-the-art BiLSTM and BiGRU on MGD database and two other benchmark databases (i.e., BUAA mobile gesture and SmartWatch gesture). The source code and MGD database will be made publicly available at https://github.com/bczhangbczhang/Fisher-Discriminant-LSTM.

Bibliographic note

This is the author’s version of a work that was accepted for publication in Pattern Recognition. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Pattern Recognition, 77, 2018 DOI: 10.1016/j.patcog.2017.12.023