Human Identity Recognition Based on Gait Trajectory Curve Features

Abstract

The invention discloses a human body identification method based on gait trajectory curve features. According to the graph of the gait acceleration data in the time domain, the problem of gait identification is transformed into a matching problem of trajectory curve shape. From the perspective of iconography, the paper uses the Fourier descriptor to describe the global trajectory curve characteristics of the thicker outline of the gait curve, and proposes the concept of the direction angle descriptor to further describe the fine local trajectory curve characteristics of the gait curve, and finally Combine the two to complete the matching of the gait trajectory curve. The results show that the gait trajectory curve features proposed in this paper can be well used for identification.

Description

technical field [0001] The invention belongs to the field of information security, and in particular relates to a human body identification method based on gait trajectory curve characteristics. Background technique [0002] According to Taiwan's "Electronic Times", statistics from the Ministry of Industry and Information Technology show that by the end of May 2014, the number of mobile phone users in China had reached 1.256 billion, an increase of 0.36% over April and an increase of 7.82% over the same period last year. In China, 90.8% of people are using mobile phones. On May 17, 2016, the Internet Society of China and the National Internet Emergency Response Center (CNCERT) jointly released the "China Mobile Internet Development Status and Security Report (2016)" for the first time in Beijing. According to the report, in 2015, the number of active mobile Internet users in China reached 780 million, accounting for 56.9% of the national population. Mobile phone security i...

AI Technical Summary

Problems solved by technology

Simple features are extracted in the time domain stage. Although the amount of calculation is small, the recognition rate obtained is not very high; in view of the above problems, the features of the frequency domain are added on this basis, because the frequency domain discards the signal features of the time domain, so generally These two types of features need to be fused, and the recognition rate has been greatly improved after fusion. However, due to the high dimensionality of the features extracted in the frequency domain stage, it is necessary to reduce the dimensionality or optimize the features. The quality of these processes will directly affect the final result

The time-frequency method can better observe information characteristics in time and frequency space, but the redundancy is large

Images