Gait Feature Extraction Using Dyadic Wavelet Transform and Structural Similarity for Gait Recognition

2019 ◽  
pp. 373-377
Author(s):  
Hajime Omura ◽  
Teruya Minamoto
Keyword(s):  
Feature Extraction ◽  
Wavelet Transform ◽  
Gait Recognition ◽  
Structural Similarity ◽  
Dyadic Wavelet ◽  
Gait Feature ◽  
Dyadic Wavelet Transform

Estimation of Heart Rate Variability Fluctuations by Wavelet Transform

2011 ◽  
Vol 57 (3) ◽  
pp. 395-400 ◽  
Author(s):  
Anton Popov ◽  
Yevgeniy Karplyuk ◽  
Volodymyr Fesechko
Keyword(s):  
Heart Rate ◽  
Heart Rate Variability ◽  
Wavelet Transform ◽  
Experimental Results ◽  
Dyadic Wavelet ◽  
Heart Rate Fluctuations ◽  
Slow Heart Rate ◽  
Dyadic Wavelet Transform

Estimation of Heart Rate Variability Fluctuations by Wavelet TransformTechnique for separate estimation of fast and slow fluctuations in the heart rate signal is developed. The orthogonal dyadic wavelet transform is used to separate the slow heart rate changes in approximation part of decomposition and fast changes in detail parts. Experimental results using the recordings from persons practicing Chi meditation demonstrated the applicability of estimation heart rate fluctuations with the proposed approach.

A Gait Feature Extraction Algorithm Based on Fusion of Spatial and Frequency Feature

2013 ◽  
Vol 291-294 ◽  
pp. 2492-2495
Author(s):  
Xiao Ke Zhu ◽  
Xiao Pan Chen ◽  
Fan Zhang
Keyword(s):  
Feature Extraction ◽  
Moving Objects ◽  
Gait Recognition ◽  
Morphological Processing ◽  
Moving Object ◽  
Classification Rate ◽  
Feature Extraction Algorithm ◽  
Extraction Algorithm ◽  
Gait Feature ◽  
Frequency Feature

In order to enhance the accuracy of gait recognition, a new gait feature extraction algorithm is proposed. Firstly, the gait images are preprocessed to extract moving objects, including background modeling, moving object extracting and morphological processing. Secondly, an equidistant slicing curve model based on system of polar coordinate is designed to slice the moving object, and the slicing vector is used to describe the spatial feature; Thirdly, the slicing vector is converted into frequency signal by Fourier transform to extract the frequency feature. Finally, the above two features are fused and used for the classification. The experimental results show that proposed algorithm provides higher correct classification rate than the algorithms using single feature, and meets the requirements of the real-time.

Sign in / Sign up

Export Citation Format

Share Document