Multi-kernel fuzzy local gabor feature extraction method for automatic gait recognition
AssigneeKing Fahd University of Petroleum and Minerals
InventorsAmer Ghazi Abdullah BINSAADOON, El-Sayed M. El-Alfy
Life of this patent
Estimating the term…
Abstract
Described is a novel method for feature extraction for automatic gait recognition. This method uses Multi-kernel Fuzzy-based Local Gabor Binary Pattern. From a captured gait video sequence, the gait period is determined then a gait energy image is constructed to represent the spatial-temporal variations during one motion cycle of the gait sequence. Then, each gait sequence is represented with a feature vector. The computation of this vector is conducted by first applying the 2D Gabor filter bank then encoding the variations in the Gabor magnitude using a multi-kernel fuzzy local binary pattern operator. Finally, gait classification is performed using a support vector machine.
Claims20
A method, performed by executing a program by one or more processors in a computer system, the method comprising:
- inputting, into the computer system, a video sequence of a moving subject;
- determining, by the one or more processors, an average image of images of the video sequence for a cycle;
- filtering, by the one or more processors, the averaged image to obtain one or more filtered responses;
- determining, by the one or more processors, the magnitudes of the filtered responses;
- for each filtered response, determining, by the one or more processors, a plurality of fuzzy local based patterns based on the magnitudes of the filtered responses;
- forming, by the one or more processors, feature vectors based on the fuzzy local based patterns.
A computer system comprising one or more processors, the one or more processors executing a program to perform steps comprising:
- inputting to the computer system a video sequence of a moving subject;
- determining an average image of images of the video sequence for a cycle;
- filtering the averaged image to obtain one or more filtered responses;
- determining the magnitudes of the filtered responses;
- for each filtered response, determining a plurality of fuzzy local based patterns based on the magnitudes of the filtered responses;
- forming feature vectors based on the fuzzy local based patterns.
Dependencies are inferred from the claim text.