A method for extracting the midline of a finger

A finger and midline technology, which is applied in the field of finger midline extraction in the field of biometric feature recognition technology, can solve the problems of unsatisfactory midline effects, limitations, and no general algorithm, etc., to avoid inaccurate positioning and strong robustness Effect

Active Publication Date: 2020-06-30
JILIN UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Restricted by the extraction algorithm of the finger root point, some points will deviate from the finger contour at the finger root position of the connecting part between the two fingers (this part of the point is not on the fitting line of the finger contour), and the existence of this part of the point will affect the finger root. The position calculation of the midpoint affects the extraction result of the midline;
[0009] (3) When using the side contour line to fit the finger contour line, the result of contour line fitting is unsatisfactory due to some points at the end points of the contour lines on both sides deviate from the finger contour line, although the result of curve fitting can be improved by removing some end points, However, the number and proportion of deviation points contained in different finger contours of different people are not uniform, and there is no effective general algorithm; for the situation where the contour fluctuations on both sides of the finger are relatively large, the midline effect extracted by the existing contour fitting method is not ideal.
[0010] (4) The method of the finger skeleton is similar to removing the end points of the finger contour. There will be some contour points at the root of the finger that do not participate in the extraction process of the midline, which will cause a waste of finger contour information.

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 method for extracting the midline of a finger
  • A method for extracting the midline of a finger
  • A method for extracting the midline of a finger

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] 1. Use the image binarization method (such as the maximum between-class variance method) to collect the palm image ( figure 1 ) for binarization processing to obtain a binarized palm image ( figure 2 );

[0040] 2. Use the contour extraction algorithm to extract the hand contour from the binarized palm image ( image 3 ), calculate the position of the wrist center point ( image 3 in the "hollow circle" position). Use the relative distance method to calculate the distance from the hand contour point to the wrist center point, calculate the derivative of the distance curve, and obtain the fingertip point ( image 3 The "pentagram" in), refers to the root point ( image 3 "*" in ) and the root point on the outside of the little finger and index finger ( image 3 "+" position in ). Extract the contours of the little finger, ring finger, middle finger and index finger according to the root point and fingertip point ( Figure 4 contours in (a-d));

[0041] 3. Use th...

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 finger midline extraction method, which belongs to the field of biological feature recognition. The steps of the present invention are to carry out binarization and contour extraction to the collected hand shape images; to detect fingertip points and finger root points by the relative distance method, and to intercept four-finger finger contours by using the fingertip points and finger root points; Use the distance-based plane area division method to extract feature points for the four-finger contour; according to the midline feature: a. The midline of the finger is located in the middle of the finger contour and must be within the finger contour; b. The points on the midline and the finger contour points on both sides The included angle must be greater than 90 degrees; the centerline of the finger is obtained by fitting a straight line to the feature points in the area near the centerline. The method for extracting the midline of the finger proposed by the present invention does not need to rely on the fingertip point and the root point of the finger, and can effectively avoid the problems of inaccurate positioning of the fingertip point and inaccurate midline extraction caused by interference points near the finger root point.

Description

technical field [0001] The invention belongs to the finger midline extraction part in the technical field of biological feature identification, and specifically designs a finger midline extraction method. Background technique [0002] In the process of using hand shape for identification, in order to extract the width feature of the finger contour, it is necessary to extract the midline of the finger. When extracting the finger midlines of hand images collected at different times, the quality of finger midline extraction is related to the performance of the entire recognition system. Therefore, it is necessary to design a robust finger midline extraction method. Existing midline extraction algorithms include: [0003] 1. Use the line connecting the fingertip point and the midpoint of the root of the finger as the midline of the finger; [0004] 2. Use the contour lines on both sides of the finger to fit the two finger contour lines, and extract the midline of the two as th...

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): G06K9/00G06K9/38G06K9/46
CPCG06V40/1347G06V10/28G06V10/44
Inventor 刘富姜守坤康冰李温温李丁园侯涛刘云王柯
Owner JILIN 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