Unlock instant, AI-driven research and patent intelligence for your innovation.

A gesture image recognition method and system

A recognition method and image histogram technology, applied in the field of image recognition, can solve the problems of lower recognition accuracy, slow recognition speed, and low recognition rate of gesture images

Inactive Publication Date: 2019-09-24
SHANGHAI XPARTNER ROBOTICS
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, many gesture recognition systems need to rely on sensor equipment, such as infrared, ultrasonic, multi-camera and other equipment, while the recognition speed is slow and the recognition rate is low.
Camera-based gesture recognition and motion recognition interaction technology, the main 3D camera uses the human body or palm as the recognition object to capture motion behavior, but due to the high flexibility of the posture change of the human body or palm, the gesture image is caused by the change of the palm posture. The recognition accuracy is reduced

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 image recognition method and system
  • A gesture image recognition method and system
  • A gesture image recognition method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0100] Such as figure 1 As shown, this embodiment provides a schematic flowchart of a gesture image recognition method, which includes:

[0101] Such as Image 6 As shown in a, step S110, acquire a basic gesture image, perform binarization processing on the basic gesture image to form a binary basic gesture image; and analyze and process the binary basic gesture image to obtain the binary gesture image. Value the reference line L in the basic gesture image; the basic gesture image is an image collected arbitrarily, wherein the basic gesture image is a gesture image at any angle, and the basic gesture image usually includes characteristic picture information and non-characteristic picture information.

[0102] Step S120, calculating the inclination angle α of the binarized basic gesture image according to the reference line L;

[0103] Such as Image 6 As shown in b, step S130, adjusting the binarized basic gesture image according to the tilt angle α to form a binarized gest...

specific Embodiment approach

[0134] The first judgment result is preset to match the fist gesture, the second judgment result is used to match the scissors gesture, and the third judgment result is used to match the palm gesture.

[0135] First obtain a basic gesture image, perform binarization processing on the basic gesture image to form a binary basic gesture image; and analyze and process the binary basic gesture image to obtain the binary basic gesture image base line L; calculate the tilt angle α of the binarized basic gesture image according to the base line L; adjust the binarized base gesture image according to the tilt angle α to form a binarized gesture adjustment image, according to Segmenting and thresholding the binarized gesture adjustment image and contour extraction to form a binarized gesture judging image, wherein, after obtaining the binarized gesture judging image, continue to acquire the contour perimeter of the binarized gesture judging image, The contour width of the binarized gest...

Embodiment 2

[0137] like image 3 As shown, a schematic flow chart of a gesture image recognition method, wherein the judgment result includes a first judgment result, a second judgment result, and a third judgment result; in step S1502, according to the perimeter of the contour, the palm The width is combined with the calculation method to identify the binarized gesture judgment image and form the judgment result, specifically including:

[0138] Step S150221, the first interval, the second interval, and the third interval are preset; wherein, the first interval is (0, M1), M1∈(2.3, 2.8), the second interval is [M1, M2), and the third interval is [M2,∞), M2∈(3.2, 3.6).

[0139] Step S150222, calculating and forming a perimeter-width ratio according to the contour perimeter, the palm width and the perimeter-width ratio algorithm;

[0140] Wherein, the perimeter width ratio algorithm is

[0141] K=L / W;

[0142] K is the ratio of perimeter to width; L is the perimeter of the outline; W i...

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

Embodiments of the present invention relate to image recognition technologies, and in particular, to a method and system for recognizing gesture images, wherein a method for recognizing gesture images is specifically: first acquiring a basic gesture image, and performing binarization processing on the basic gesture image to form a Binarize the basic gesture image; continue to analyze and process the binarized basic gesture image to obtain the baseline in the binarized basic gesture image, adjust the basic gesture image through the baseline to make the basic gesture image in a standard state, and pass the segmentation threshold The non-characteristic picture information in the gesture image is removed, only the characteristic picture information is extracted, and the judgment result is formed by identifying the characteristic picture information. Using this method, on the one hand, reduces the amount of basic data for image recognition and improves the recognition of gesture images. On the other hand, the basic gesture image can be kept in a standard state, and the recognition accuracy can be improved.

Description

technical field [0001] Embodiments of the present invention relate to image recognition technologies, and in particular to a gesture image recognition method and system. Background technique [0002] With the development of computer technology, human-computer interaction has become an indispensable part of people's life, but most of the interaction is based on the two-dimensional interaction technology of mouse, keyboard, handheld device and window interface. How to make the interaction more Nature has become a hot research topic in recent years. As one of the main means of human interaction, gestures have a history even earlier than spoken language, so using gestures as human-computer interaction will be more friendly, convenient, concise, and intuitive, and it will naturally become an extension of traditional human-computer interaction. At present, many gesture recognition systems need to rely on sensor devices, such as infrared, ultrasonic, multi-camera and other devices...

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): G06K9/00
CPCG06V40/28
Inventor 恽为民夏晓斌龚成庞作伟
Owner SHANGHAI XPARTNER ROBOTICS