Intelligent device gesture recognition control method based on image recognition

A gesture recognition, smart device technology, applied in neural learning methods, character and pattern recognition, graphic reading, etc., can solve problems such as inapplicability, and achieve the effect of wide use of scenes, high custom space, and high precision

Pending Publication Date: 2022-07-26
YANGZHOU UNIV
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional input devices may not be suitable in some cases, such as touch screen interaction will be affected by distance restrictions or water or other dirty hands

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
  • Intelligent device gesture recognition control method based on image recognition
  • Intelligent device gesture recognition control method based on image recognition
  • Intelligent device gesture recognition control method based on image recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] like figure 1 An image recognition-based gesture recognition control method for a smart device includes the following steps:

[0049]Step 1) capture the user image through the camera, and identify the user identity and the approximate position of the hand based on OpenCV2;

[0050] Step 1.1) The user collects the face image through the camera, and judges the user's identity through the face recognition model; if it is detected that the user is an authorized user, step 1.2) is performed;

[0051] Step 1.2) Using the mediapipe model based on OpenCV2, define a hand function to perform preliminary segmentation on the input image to obtain the user's hand rectangle position information;

[0052] The obtained hand rectangle position information is:

[0053] The coordinates of the upper left corner of the rectangle landmarks(x,y)

[0054] Rectangle size shape(width, height)

[0055] Step 2) performing grayscale and binarization operations on the image information of the re...

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 an intelligent device gesture recognition control method based on image recognition, and the method comprises the steps: 1), capturing a user image through a camera, and recognizing the identity of a user and the general position of a hand based on OpenCV2; 2) graying and binarizing the image information of the rectangular part of the hand, solving the center distance of the hand graph to judge the palm center position, and analyzing the position coordinates of the key points of the hand by adopting a CNN model; (3) comparing and judging the hand key point position coordinates obtained in the step (2) with an operation gesture preset by a user by using a cosine similarity method by calculating a two-dimensional angle relation and other motion information of the hand key point position coordinates, so as to realize gesture analysis; 4, according to the analyzed gestures, a control instruction is sent to the equipment according to control logic set by a user, and the equipment is operated across the air through the gestures. According to the method, the neural network is used for recognizing the hand positions and gestures, inductive analysis on the gestures is introduced, and the intelligent equipment is rapidly controlled through the recognition result.

Description

technical field [0001] The present invention relates to the technical field of equipment, in particular to a gesture recognition control method for smart equipment based on image recognition. Background technique [0002] The current input methods of smart devices are mainly keyboard and mouse and touch screen input, and traditional input devices may not be applicable in some cases, such as being limited by distance or having water or other dirt on the hands. However, the existing gesture recognition control mainly recognizes the movement trajectory of the user's hand through the detection sensor, performs relevant analysis and outputs the operation signal. This method can only recognize the simple trajectory, but not the user's specific hand posture. Analysis and feedback. [0003] At present, most of the existing methods for identifying specific gestures are to classify gestures through pattern recognition, to establish a decision tree model by extracting the apparent fea...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06V40/20G06V20/40G06V10/74G06V10/764G06V10/82G06N3/04G06N3/08G06K9/62G06F3/01
CPCG06N3/08G06F3/017G06N3/047G06N3/048G06N3/045G06F18/22G06F18/2415
Inventor 沙志清朱毅毕易戴悦纪正一
Owner YANGZHOU UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap