Eyelid positioning method based on strong direction weighted edge detection and RNL goodness of fit

A technology of goodness of fit and edge detection, applied in the acquisition/recognition of eyes, instruments, characters and pattern recognition, etc., can solve the problems of missing iris information, slow positioning speed, and low positioning accuracy.

Pending Publication Date: 2020-11-17
HANGZHOU DIANZI UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The advantages and disadvantages of the two are often complementary. Using linear fitting to locate eyelids has low computational complexity and fast positioning speed, but the positioning accuracy is low, which will cause a large number of missing iris information; parabolic fitting has high positioning accuracy, but high computational complexity. slow positioning

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
  • Eyelid positioning method based on strong direction weighted edge detection and RNL goodness of fit
  • Eyelid positioning method based on strong direction weighted edge detection and RNL goodness of fit
  • Eyelid positioning method based on strong direction weighted edge detection and RNL goodness of fit

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The present invention will be further described in detail in conjunction with the following specific embodiments and accompanying drawings.

[0021] Step (1). Segment the upper and lower eyelids according to the position of the center of the iris to determine the area of ​​the upper and lower eyelids; specifically: according to the coordinates of the center of the iris, take the line connecting the center of the circle and the inner and outer corners of the eye as the dividing line, and the upper eyelid and iris The area between the dividing lines is the upper eyelid area, and the area between the dividing line within the iris range and the lower eyelid is the lower eyelid area.

[0022] Step (2). Use the edge-preserving denoising smoothing filter operator weighted in the strong direction to perform preprocessing before eyelid detection.

[0023] In this embodiment, according to the characteristics that the physiological extension direction between the eyelashes and the...

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 an eyelid positioning method based on strong direction weighted edge detection and RNL goodness of fit. An existing straight line fitting positioning method is high in positioning speed but low in positioning precision. The parabola fitting positioning method is high in fitting positioning precision, but low in positioning speed. The method comprises the following steps: segmenting upper and lower eyelids according to an iris circle center position, and determining upper and lower eyelid areas; secondly, preprocessing an image before eyelid detection by using a strong direction weighted edge-preserving denoising smoothing filtering operator; secondly, suppressing eyelash interference by using a strong direction weighted edge detection operator, and dynamically selecting edge detection operator parameters according to gray scale contrast values of regions above and below the eyelid edge in the iris image to obtain candidate eyelid edges to be fitted; and finally,fitting eyelid edges by adopting a least square method parabola, and screening eyelid edge selection points by taking RNL goodness of fit as an index to finish eyelid positioning. The method has goodrobustness, and an ideal positioning result can be obtained even for an upper eyelid which is shielded by eyelashes.

Description

technical field [0001] The invention belongs to the technical field of biological feature recognition and information security, and relates to a strong direction weighted edge detection and R NL A goodness-of-fit method for eyelid localization. Background technique [0002] Iris recognition is a biometric technology, which has many good characteristics suitable for identity features, including universality, uniqueness, stability, protection, etc. Compared with other biometric identification technologies, iris recognition is a more accurate and reliable identification method. Eyelid localization is a key technology that affects iris recognition performance. In iris recognition, eyelid localization is actually detecting and localizing the lid margins of the upper and lower eyelids in iris samples. [0003] Up to now, eyelid positioning methods can be roughly divided into two categories, one is linear fitting positioning eyelids, and the other is parabolic fitting positionin...

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 Applications(China)
IPC IPC(8): G06K9/00
CPCG06V40/193
Inventor 叶学义季必胜陈妍婷张珂坤陈华华
Owner HANGZHOU DIANZI 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

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