Gesture recognition method, device and gesture learning system

A gesture recognition and gesture technology, applied in the field of pattern recognition, can solve problems such as inability to recognize static sign language, and achieve the effect of eliminating communication barriers, simple methods, and reducing algorithm complexity.

Active Publication Date: 2020-02-07
SUZHOU KEDA TECH +1
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Therefore, the technical problem to be solved in the present invention is to overcome the defect that static sign language cannot be recognized in the prior art, thereby providing a gesture recognition method, including the following steps:

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
  • Gesture recognition method, device and gesture learning system
  • Gesture recognition method, device and gesture learning system
  • Gesture recognition method, device and gesture learning system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0071] This embodiment provides a gesture recognition method, such as Figure 1A shown, including the following steps:

[0072] S1: Obtain the extended state of each finger of the target gesture.

[0073] Normally, a hand has 5 fingers, namely thumb, index finger, middle finger, ring finger and little finger. In addition to the thumb, each finger has 4 bones, namely the metacarpal, proximal phalanx, middle phalanx, and distal phalanx. The extended state of each finger, including the bent state of each finger, for example, as Figure 1B In the gesture representation manner of the 26 letters shown, the four fingers are fully stretched when representing the letter B, the four fingers are bent when representing the letter C, and the four fingers are clenched when representing the letter D.

[0074] As a preferred implementation of this embodiment, the extended state of each finger of the target gesture is acquired through the Leap Motion sensor. Leap Motion's core equipment inc...

Embodiment 2

[0105] This embodiment provides a gesture recognition device, such as Figure 2A As shown, it includes a first acquisition unit 10 , a first matching unit 20 , a second acquisition unit 30 and a second matching unit 40 .

[0106] The first acquisition unit 10 is configured to acquire the extended state of each finger of the target gesture.

[0107] The first matching unit 20 is configured to select a gesture set that matches each finger extension state of the target gesture from the preset gesture library.

[0108] The second acquiring unit 30 is configured to acquire gesture feature quantities of the target gesture. The gesture feature quantity includes one or more of palm orientation, hand extension direction, index finger proximal knuckle direction, thumb-to-index fingertip distance, index finger-to-middle finger-tip distance.

[0109] The second matching unit 40 is configured to select a gesture that matches the gesture feature value of the target gesture from the gestur...

Embodiment 3

[0122] This embodiment provides a gesture learning system, such as image 3 As shown, it includes a display unit, the gesture recognition device described in Embodiment 2, and a feedback unit.

[0123] The display unit is used for displaying preset examples of gestures to be learned for users to imitate. The system has preset examples of gestures stored in advance, and users can choose the gestures they want to learn from the system according to their own interests. After the user selects, the system will display a preset example of the gesture selected by the user for the user to imitate. Preferably, the display unit is also used to display the 3D image of the user's hand movement in real time.

[0124] The gesture recognition device described in Embodiment 2 is used to recognize the target gesture imitated by the user. As a preferred implementation of this embodiment, the Leap Motion sensor is used to track the user's hand movements and collect hand feature data. The use...

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

A gesture recognition method, device, and gesture learning system, which acquire the extended state of each finger of a target gesture; select a gesture set that matches the extended state of each finger of the target gesture from a preset gesture library; obtain the The gesture feature value of the target gesture; selecting a gesture from the gesture set that matches the gesture feature value of the target gesture. The gesture recognition method, device and gesture learning system can accurately recognize static gesture language, and can recognize rich semantics expressed by gestures, eliminating communication barriers between gesture language and natural language.

Description

technical field [0001] The invention relates to the field of pattern recognition, in particular to a gesture recognition method, device and gesture learning system. Background technique [0002] Comparing actions with gestures, simulating images or words to form a certain meaning, is a hand language for people with hearing impairments to communicate and exchange ideas with each other, and it is also an important auxiliary tool for vocal language. Sign language teaching often adopts face-to-face teaching, which requires a lot of teacher resources; or uses diagrams and text descriptions, but it is often difficult for students to judge the accuracy of gestures in the self-learning process. [0003] The somatosensory game product "Leap Motion" (English: Leap Motion) provides real-time data by binding hands, fingers or tools within the field of vision, and can recognize specific motion patterns that can display user intentions or instructions as gestures. However, Leap Motion ca...

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 Patents(China)
IPC IPC(8): G06F16/00
CPCG06V40/107G06V40/28
Inventor 季怡曹李军陈卫东
Owner SUZHOU KEDA TECH
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