Supercharge Your Innovation With Domain-Expert AI Agents!

A gesture recognition system and method based on K-nearest neighbor algorithm

A K-nearest neighbor algorithm and gesture recognition technology, applied in the field of gesture recognition, to achieve the effect of large degree of freedom of gestures and fewer sensor slices

Inactive Publication Date: 2019-01-18
SUZHOU UNIV
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the above-mentioned patent uses the K-nearest neighbor classifier for the recognition of the shape of the human hand, and there is still no technical solution for using the K-nearest neighbor algorithm for gesture recognition

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A gesture recognition system and method based on K-nearest neighbor algorithm
  • A gesture recognition system and method based on K-nearest neighbor algorithm
  • A gesture recognition system and method based on K-nearest neighbor algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] This embodiment introduces the hardware equipment of the embedded intelligent gesture recognition system based on the K-nearest neighbor algorithm of the present invention.

[0038] Based on the sensor chip FDC2214 of TI company, a gesture recognition device is designed and manufactured to realize the judgment of guessing and punching. The device has two working modes of training and judgment. In the judgment mode, the experimental device can judge the designated personnel for guessing and throwing punches. Here, the guessing judgment refers to the accurate judgment of gestures "rock", "scissors" and "cloth", and the judgment of punching refers to the accurate judgment of gestures "1", "2", "3", "4" and "5". In the training mode, any person can be trained in the gestures of the guessing game and the punching game. After a limited number of trainings, the correct judgment of the guessing game and the punching game can be made.

[0039] FDC2214 is a capacitive detection...

Embodiment 2

[0045] This embodiment introduces the working method and software algorithm flow of the embedded intelligent gesture recognition system based on the K-nearest neighbor algorithm of the present invention.

[0046] (1) Capacitance measurement method of FDC2214

[0047] The input end of each detection channel of the FDC2214 chip is connected with an inductor and a capacitor to form an LC resonant circuit. The sensing end of the measured capacitance is connected to the LC circuit, which will generate an oscillation frequency, and the measured capacitance value can be calculated according to the frequency value. Basic physical formulas based on common knowledge

[0048]

[0049] It can be seen that the capacitance is related to the distance between the two plates and the area between the plates. When making different gestures "rock, scissors, cloth, 1, 2, 3, 4, 5", due to the distance between the sensor and each gesture Different areas lead to different capacitances detected by...

Embodiment 3

[0056] This embodiment introduces the circuit and program design of the embedded intelligent gesture recognition system based on the K-nearest neighbor algorithm of the present invention.

[0057] Such as Figure 4 As shown, it is the FDC2214 capacitive sensor circuit design of the present invention. Connect an inductor and a capacitor to the input end of each detection channel of the chip to form an LC circuit. The sensor terminal of the measured capacitance is connected to the LC circuit to generate an oscillation frequency, and the measured capacitance value can be calculated according to the frequency value.

[0058] Such as Figure 5 Shown is the STM32 programming flow chart of the present invention. When specifically judging a certain gesture, the present invention adopts the K nearest neighbor algorithm. The specific content of the algorithm is: given the training data set of each gesture and calculating the mean value, for a new input instance, calculate the Euclide...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a gesture recognition system and a method based on a K-nearest neighbor algorithm, comprising a main controller module (1), a capacitive sensor chip (2) connected with the maincontroller module (1), a display module (4), a key (5), and a power supply (6), and a metal sensor (3) connected with the capacitive sensor chip (2). According to the invention, the training data sets of each gesture are learned and the average value is calculated, the Euclidean distance between the new input instance and the average value of each gesture data set is calculated, if the Euclideandistance between the input instance and the average value of a gesture data set is minimum, the input instance can be judged as the gesture. The invention has the advantages of small number of sensorpieces, large degree of freedom of gesture, testability, rapidity and accuracy, and can be tested by both left and right hands.

Description

technical field [0001] The invention belongs to the technical field of gesture recognition, and in particular relates to a gesture recognition system and method based on a K-nearest neighbor algorithm. Background technique [0002] With the increase of smart electronic devices and the development of human-computer interaction technology, gesture interaction technology has gradually become a research hotspot. Gesture interaction is the use of computer graphics and other technologies to recognize human body language and convert it into commands to operate equipment. Gesture interaction is a new human-computer interaction method after the mouse, keyboard and touch screen. And with the unprecedented popularity of virtual reality augmented reality (Virtual Reality Augmented Reality, VRAR), gesture interaction technology will develop rapidly in the next few years. [0003] Among gesture interaction technologies, gesture recognition is a key technology. In the gesture recognition...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/28G06F18/24147
Inventor 陈蓉陶砚蕴高天晴王子悦蔡兴强
Owner SUZHOU UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More