Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Hand shape classification method based on image processing

A classification method and image processing technology, applied to instruments, character and pattern recognition, computer components, etc., can solve problems such as inconsistent standards, time-consuming and labor-intensive errors of manual measurement, and strong subjectivity of manual observation

Inactive Publication Date: 2020-01-17
HARBIN UNIV OF SCI & TECH
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] It can be seen that the application prospect of hand type classification is very broad. The traditional hand type classification method mainly relies on manual measurement or manual observation. , accurate and objective hand classification method is particularly important

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
  • Hand shape classification method based on image processing
  • Hand shape classification method based on image processing
  • Hand shape classification method based on image processing

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0043] The present invention first provides a hand type classification method based on image processing, such as figure 1 As shown, the specific method is as follows:

[0044] Step 1, image acquisition is performed on the hand of the subject to obtain a complete hand image;

[0045] Step 2, building a skin color model for the collected hand image and selecting a threshold for binarization, and storing the obtained hand binarized image;

[0046] Step 3, edge detection is performed on the binarized image obtained in step 2, and the obtained palm outline image is stored, and one of the acquisition methods can be realized by the Canny operator in OpenCV;

[0047] Step 4, performing an open operation on the palm contour image obtained in step 3 to obtain a smooth palm contour image;

[0048] Step 5. Calculate the length of the palm respectively (L 1 ), the length of the middle finger (L 2 ) and palm width (L 3 );

[0049] Step 6, use type to represent the characteristic value...

specific Embodiment approach 2

[0052] The difference from the specific embodiment 1 is that in this embodiment, a hand type classification method based on image processing, the schematic diagram of the shooting system used to collect the image of the subject's hand in the first step is as follows: figure 2 As shown, the specific shooting method is as follows: Let the five fingers of the right hand of the volunteers open naturally, put the palms down and flat on the designated frame on the table, and the camera located directly above the palms of the testees shoots vertically downwards to ensure that both the palms and wrists can be photographed , to obtain the hand image, and adopt uniform size image resolution when collecting the image of the subject's hand.

specific Embodiment approach 3

[0054] On the basis of specific embodiment one, L 1 , L 2 and L 3 specific measurement methods such as image 3 As shown, the measurement flow chart is as follows Figure 4 shown.

[0055] Measure L 1 , L 2 and L 3 The method is:

[0056] a) Obtain the convex hull of the outer contour of the entire hand. In image processing, the convex hull can be regarded as a convex set surrounding the outermost layer of the image, and one of the acquisition methods can be realized by the convexHull function in OpenCV;

[0057] b) Determining the convex hull defect (A 2 ) and defect origin (A 1 );

[0058] c) Find the relative position of the palm and fingers, and calibrate the center point of the palm (A 0 ) and profile (B 1 );

[0059] d) Use the center point of the palm and the radius of the palm to obtain the coordinates of the lowest point of the palm outline, and eliminate the part of the wrist image below the lowest point;

[0060] e) Get middle finger tip A 1 , the lo...

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 hand shape classification method based on image processing, and particularly relates to a hand image processing technology. The method comprises the following steps: acquiring a hand image of a testee; establishing a skin color model selection threshold to binarize the image; performing edge detection on the binary image, and storing an obtained palm contour image; performing opening operation on the palm contour image to obtain a smooth palm contour image; finding out a palm contour convex hull, and calculating the length (L1) of the palm, the length (L2) of the middle finger and the width (L3) of the palm; calculating a hand characteristic value type; and determining that the hand shape of the testee is one of a slender hand shape, a normal hand shape and a fathand shape according to the threshold value. According to the method, the problems that a traditional hand shape classification method mainly depends on manual measurement or manual observation, timeand labor are wasted in manual measurement, errors are large, subjectivity of manual observation is high, and standards are not unified are solved, and the rapid, accurate and objective hand shape classification method is provided.

Description

technical field [0001] The invention relates to a hand type classification method based on image processing, in particular to image processing technology and calculation of hand feature values. Background technique [0002] In the past few decades, computer technology has developed rapidly, and people in all walks of life have become more and more dependent on computers. Therefore, the information interaction between human and computer has been paid more and more attention. Nowadays, the form of human-computer interaction has entered the multi-channel and multi-modal stage, and gesture recognition is a mainstream trend at this stage. However, the current gesture recognition algorithms directly extract the user's gesture features, ignoring the differences between each person's hand shape. When different hand types use the same standard value, erroneous judgments may occur. If the hand type of the user can be judged before performing gesture recognition, and then the gesture...

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
CPCG06V40/113G06F18/2415
Inventor 王鹏刘尚昆宋成伟李翰堂刘铖胡振东
Owner HARBIN UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com