Unlock instant, AI-driven research and patent intelligence for your innovation.

Iris feature extraction method based on FREAK description

A feature extraction, iris technology, applied in the acquisition/recognition of eyes, special data processing applications, image data processing, etc., can solve the problems of low recognition performance, low real-time performance, etc., to improve discrimination, reduce correlation, and improve reliability. awesome effect

Pending Publication Date: 2021-03-09
HANGZHOU DIANZI UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, most of them use Gabor filter to filter the iris texture and encode it according to the filtered feature map. However, this method relies on the acquisition of high-definition iris images, and it is not ideal for non-ideal iris recognition with uneven illumination and blurred textures. On the other hand, the recognition performance has dropped significantly, and there are recent non-ideal iris recognition methods based on local invariant features of feature points, such as the scale-invariant feature transform (SIFT) iris recognition method: Region-based SIFT approach to irisrecognition, Optics and Lasers in Engineering, 2009, and the accelerated robust feature (SURF) method: Speeded up robust features for efficient iris recognition, which is robust to lighting and iris texture blur, but the real-time performance of these methods is not high

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
  • Iris feature extraction method based on FREAK description
  • Iris feature extraction method based on FREAK description
  • Iris feature extraction method based on FREAK description

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The present invention will be further described below in conjunction with the accompanying drawings.

[0020] A method of iris feature extraction based on FREAK description, such as figure 1 As shown, the specific steps are as follows:

[0021] Step 1: Iris feature point detection:

[0022] a. Gaussian functions with different scale factors σ are used to convolve with the iris image and then down-sampled 3 times to construct 3 groups of 5-layer Gaussian scale spaces. The method is as follows:

[0023] L(x,y,σ)=I(x,y)*G(x,y,σ) (1)

[0024]

[0025] Among them: L(x, y, σ) is the scale space representation of the iris image, I(x, y) is the iris image, G(x, y, σ) is the Gaussian kernel, * is the convolution operation, and σ is the scale space Factor, the value of σ determines the degree of blurring and smoothing of the iris image. When σ changes continuously, L(x, y, σ) constitutes the scale space representation of the iris image. The difference between the 5 layers ...

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 iris feature extraction method based on FREAK description. According to the invention, the Gaussian difference gold sub-tower model in the SIFT algorithm is adopted to detect the stable feature point set from multiple scales of the iris texture, and the FREAK descriptor is utilized to encode according to the pixel intensity relationship around the feature points, so thatthe situation that the original SIFT algorithm encodes according to the complex gradient information of the pixels is abandoned; quick characterization of iris underlying features is realized, and the anti-interference capability is improved; in addition, through effective reconstruction of the original feature vectors, the correlation between the feature vectors is reduced, and the discrimination of iris feature point representation is improved.

Description

technical field [0001] The invention belongs to the technical field of biological feature identification and information security, in particular to an iris feature extraction method based on FREAK description. Background technique [0002] In recent years, iris recognition has developed rapidly in the past ten years because of its uniqueness, non-contact, universality, and acceptability. It has made great progress in the core algorithm of the iris recognition system, but with the continuous update of requirements , iris recognition technology also needs continuous improvement. [0003] Iris recognition is a biometric recognition technology that uses computer vision to locate its iris in an image or video and identify its identity. Iris recognition mainly has the following steps: iris acquisition, iris segmentation, iris characterization and iris matching. [0004] In recent years, domestic and foreign scholars have proposed some related algorithms for the iris recognition ...

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): G06K9/00G06F17/15G06T5/00
CPCG06F17/15G06F17/153G06T2207/30041G06V40/197G06V40/193G06T5/70
Inventor 季毕胜叶学义应娜邹茹梦廖奕艺
Owner HANGZHOU DIANZI UNIV