Skip to main content

Research Repository

Advanced Search

A novel dynamic gesture understanding algorithm fusing convolutional neural networks with hand-crafted features

Liu, aYanhong; Song, Shouan; Yang, Lei; Bian, Guibin; Yu, Hongnian

Authors

aYanhong Liu

Shouan Song

Lei Yang

Guibin Bian



Abstract

Dynamic gestures have attracted much attention in recent years due to their user-friendly interactive characteristics. However, accurate and efficient dynamic gesture understanding remains a challenge due to complex scenarios and motion information. Conventional handcrafted features are computationally cheap but can only extract low-level image features. This leads to performance degradation when dealing with complex scenes. In contrast, deep learning-based methods have a stronger feature expression ability and hence can capture more abstract and high-level image features. However, they critically rely on a large amount of training data. To address the above issues, a novel dynamic gesture understanding algorithm based on feature fusion is proposed for accurate dynamic gesture prediction. It leverages the advantages of handcrafted features and transfer learning. Aimed at small-scale dynamic gesture data, transfer learning is introduced for capturing effective feature expression. To precisely model the critical temporal information associated with dynamic gestures, a novel feature descriptor, namely, , is proposed for effective feature expression of dynamic gestures from the spatial and temporal domain. On this basis, a decision-level feature fusion framework based on support vector machine (SVM) and Dempster–Shafer (DS) evidence theory is constructed to utilize handcrafted features and to realize high-precision dynamic gesture understanding. To verify the effectiveness and robustness of the proposed recognition algorithm, analysis and comparison experiments are performed on the public Cambridge gesture dataset and Northwestern University hand gesture dataset. The proposed gesture recognition algorithm achieves prediction accuracies of 99.50% and 96.97% on these two datasets. Experimental results show that the proposed recognition framework exhibits a better recognition performance in comparison with related prediction algorithms.

Citation

Liu, A., Song, S., Yang, L., Bian, G., & Yu, H. (2022). A novel dynamic gesture understanding algorithm fusing convolutional neural networks with hand-crafted features. Journal of Visual Communication and Image Representation, 83, Article 103454. https://doi.org/10.1016/j.jvcir.2022.103454

Journal Article Type Article
Acceptance Date Feb 5, 2022
Online Publication Date Feb 15, 2022
Publication Date 2022-02
Deposit Date Feb 21, 2022
Journal Journal of Visual Communication and Image Representation
Print ISSN 1047-3203
Publisher Elsevier
Peer Reviewed Peer Reviewed
Volume 83
Article Number 103454
DOI https://doi.org/10.1016/j.jvcir.2022.103454
Keywords Dynamic gesture understanding, Transfer learning, Feature fusion, Dempster–Shafer evidence theory, Support vector machine
Public URL http://researchrepository.napier.ac.uk/Output/2847075