Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A Quadruple Finger Alignment Method Based on Feature Point Set Segmentation and RST Invariant Feature

A technology of feature point sets and feature point pairs, applied in character and pattern recognition, instruments, computer components, etc., can solve problems such as complex algorithms, low precision, and poor real-time performance

Active Publication Date: 2017-10-20
HANGZHOU JINGLIANWEN TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the disadvantages of complex algorithms, poor real-time performance, and low precision in the comparison of the existing joint-finger graphs, the present invention provides a simplified comparison process with good real-time performance and high precision. Quadruplet comparison method based on feature point set segmentation and RST invariant features

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 Quadruple Finger Alignment Method Based on Feature Point Set Segmentation and RST Invariant Feature
  • A Quadruple Finger Alignment Method Based on Feature Point Set Segmentation and RST Invariant Feature
  • A Quadruple Finger Alignment Method Based on Feature Point Set Segmentation and RST Invariant Feature

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] The present invention will be further described below in conjunction with the accompanying drawings.

[0053] refer to Figure 1 to Figure 8 , a quadruple finger comparison method based on feature point set segmentation and RST invariant features, comprising the following steps:

[0054] 1) Carry out the cutting based on the statistical histogram of the set of co-reference feature points;

[0055] 1.1) Calculate the statistical histogram of the quadruplet finger feature points with respect to the X coordinate. Since the joint finger image is much larger than the general fingerprint image, as shown in the reference figure 2 . Especially when taking pictures with a high-resolution scanner or a high-definition camera, the value of the X coordinate of the feature point is relatively large, which can reach more than 2000. For example, refer to image 3 . In order to speed up the processing speed and facilitate the calculation, when the histogram of the X coordinate is ...

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 four-finger comparison method based on feature point set segmentation and RST invariant features, comprising the following steps: 1) cutting the set of joint-finger feature points based on a statistical histogram; 2) further screening of each finger feature point, Select effective feature points; 3) Single-finger comparison, using the single-finger comparison method based on RST invariant features, first construct a 12-point circle nearest neighbor feature structure, then perform preliminary verification on feature point pairs, and then perform triangular Similarity verification; 4) use the single-finger comparison algorithm in step 2) to use the feature point set of the N fingers of the quadruple-finger sample A and the feature point set of the M fingers of the quadruple-finger sample B) Identify to obtain the similarity between A and B; 5) According to the similarity obtained in 4), determine whether the two quadruplet samples A and B come from the same hand. The invention simplifies the comparison process, has good real-time performance and high precision.

Description

technical field [0001] The invention relates to the technical fields of image processing, feature selection, fingerprint comparison, etc., especially a method for segmentation, screening and comparison of four-finger feature point sets, which can be used for quadruple fingerprints obtained by a multi-fingerprint collector. Fingers, four fingers coated with ink pad and scanned on A4 paper, quadruple fingers captured by mobile phone or camera. Background technique [0002] With the continuous improvement of image processing and pattern recognition technology, fingerprint recognition technology is widely used in people's production and life. At present, the single fingerprint identification technology is relatively mature; however, according to the matching index principle in the process of fingerprint identification, there will inevitably be some false recognition rate and false rejection rate in the single fingerprint identification process, which will affect life and product...

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): G06K9/00G06K9/34
Inventor 张永良黄聪敏
Owner HANGZHOU JINGLIANWEN 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
Eureka Blog
Learn More
PatSnap group products