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

Body iris texture non-linear normalizing method

An iris texture and normalization technology, applied in the field of image processing, can solve the problems of complex iris deformation model and no application of iris recognition field.

Inactive Publication Date: 2006-05-24
SHANGHAI JIAO TONG UNIV
View PDF0 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the iris deformation model proposed in this paper is too complex and has not been applied in the field of iris recognition.

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
  • Body iris texture non-linear normalizing method
  • Body iris texture non-linear normalizing method
  • Body iris texture non-linear normalizing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0045] An example of normalizing a real eye image using the method proposed by the present invention is given below.

[0046] Figure 4 (a) is the eye grayscale image actually collected by a special iris instrument, with a size of 320×240 (pixels).

[0047] First, the inner and outer edges of the iris are located in the eye image using Hough transform, and the iris area is segmented from the original image. Such as Figure 4 (b) shown. Then, take the center of the inner circle as the reference center, and take λ ref = 0.4505 (average of λ across all images in the iris library). Using the aforementioned method, the original circular iris area is normalized into a 256×64 rectangular area, such as Figure 4 (c) shown.

[0048] It can be seen that the texture in the result image can well reflect the texture in the original iris image, and overcome the translation, overall zoom and radial zoom caused by pupil zoom, which facilitates the subsequent iris feature extraction and ...

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

Using circular arc structure carries out radial, non-linear normalizing annular iris area. Thus, all images of iris in test base possess same scaling amplitude. Annular iris area possesses same proportion between inner and outer radiuses Lambda = r / R. even sampling is carried out on concentric sampling rings with distribution of even radial distance on annular iris area under unitive proportion. The ring is outspread to rectangle region. Backtrack method in adopted in the invention. The normalized image is better to reflect texture in original iris image. The invention overcomes issue of radial zoom caused by shift, integral zoom and pupil zoom, increasing recognition rate.

Description

technical field [0001] The invention relates to a method in the technical field of image processing, in particular to a method for nonlinear normalization of human iris texture. Background technique [0002] Iris recognition technology utilizes the lifelong invariance of human iris texture and the characteristics of individual differences to realize identity recognition. Compared with other biological features, such as fingerprints, faces, palm prints, voice, etc., it can have a higher accuracy recognition rate. Due to the change of the position and distance of the subject's eyes when taking the iris image, the size of the captured eye image will be different; in addition, the zoom degree of the pupil is different under different external lighting conditions, so it is very necessary to The iris image is calibrated or normalized to eliminate the impact of translation and scaling (including the scaling of the overall image and the scaling of the radial pupil) on the recogniti...

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): G06K9/00
Inventor 施鹏飞袁晓燕
Owner SHANGHAI JIAO TONG UNIV
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