ELM-based multi-granularity iris recognition method

An iris recognition and multi-granularity technology, which is applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of long neural network recognition time, increase the computational complexity and recognition time of recognition algorithms, and achieve high recognition accuracy, The effect of meeting the requirements of high recognition and real-time performance and avoiding one-sided defects

Inactive Publication Date: 2017-02-22
XIDIAN UNIV
View PDF1 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These methods have improved the correct recognition rate of iris to a certain extent, but there are still some shortcomings. For example, the recognition time of BP neural network is longer, and SVM is mainl

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
  • ELM-based multi-granularity iris recognition method
  • ELM-based multi-granularity iris recognition method
  • ELM-based multi-granularity iris recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] In recent years, because the iris has good stability and strong non-invasiveness, it has more application fields than fingerprints and facial recognition, and has received more and more attention. Therefore, it is more and more widely used in many fields such as e-commerce, access control and time attendance. The development status of iris recognition technology is as follows:

[0036] In terms of iris feature extraction, the iris features extracted by Gabor filtering method, wavelet zero-crossing detection method, correlation analysis method and low-pass filtering method have better recognition characteristics, but using a single Gabor filter is easy to discard effective iris information. However, wavelet zero-crossing detection and correlation analysis methods only use iris edge texture information with little information.

[0037]In terms of iris recognition algorithms, the neural networks used in the iris recognition neighborhood mainly include: BP neural network a...

Embodiment 2

[0057] The multi-granularity iris recognition method based on ELM is the same as embodiment 1, wherein 4 texture features of the gray level co-occurrence matrix described in step (3) are at the pixel pair (i, j) distance d=1, and the scanning direction is respectively θ=0 °, θ=45°, θ=90°, θ=135°, the calculation formulas of the above four texture features are as follows:

[0058] (3.1): Angular second moment (UNI), also called energy, is the sum of squares of the gray level co-occurrence matrix, which reflects the uniformity of image gray level distribution and texture thickness;

[0059]

[0060] (3.2): Entropy (ENT), entropy is a measure of the amount of information an image has, a measure of randomness, which represents the degree of inhomogeneity or complexity of the texture in the image;

[0061]

[0062] (3.3): Contrast (CON), that is, the moment of inertia, it directly reflects the contrast between the brightness of a certain pixel value and its neighboring pixel ...

Embodiment 3

[0070]The multi-granularity iris recognition method based on ELM is the same as embodiment 1-2, wherein described in step (4.1) by 4 directions, the 2D-Gabor filter bank that 20 filters that 5 frequencies are formed construct, wherein 4 The first directions are: θ=0°, 45°, 90°, 135°, here is the filtering direction of the filter, which is different from the scanning direction concept in the gray level co-occurrence matrix, and the five frequencies are: f=0.25, f=0.167, f=0.125, f=0.0625, f=0.0417, these 5 frequencies are selected in the present invention because compared with other frequencies, these 5 frequencies have better filtering effects in the simulation of the present invention.

[0071] In actual operation, 20 different filters can be formed by selecting suitable four directions and five frequencies according to the actually collected iris image and the normalized iris image.

[0072] In order to prove that the filtering effects of different frequency and different di...

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 ELM-based multi-granularity iris recognition method and solves the problems of incomplete extracted features and low recognition speed in an existing iris recognition method. The method comprises the steps of performing image acquisition and marking; performing image preprocessing; performing a gray-level co-concurrence matrix feature extraction process; performing a 2D-Gabor filter group feature extraction process; constructing a multi-granularity eigenvector; obtaining an iris recognition model; performing iris category testing; and calculating recognition precision. According to the method, a gray-level co-concurrence matrix is combined with a 2D-Gabor filter group to generate the multi-granularity eigenvector, and the multi-granularity eigenvector contains not only high-frequency texture information but also low-medium-frequency texture information, so that the multi-granularity eigenvector contains relatively comprehensive iris features, the iris recognition characteristics are enhanced, and the iris recognition precision is improved; and an ELM (Extreme Learning Machine) is applied to the iris recognition process, so that the iris recognition speed is increased. The method is suitable for the security information field with relatively high requirements on the recognition precision and the real-time property.

Description

technical field [0001] The invention belongs to the field of biometric identification, and mainly relates to iris identification, in particular to an ELM-based multi-granularity iris identification method. It is widely used in many technical fields such as e-commerce, access control and time attendance. Background technique [0002] Current biometrics mainly include: fingerprints, face shapes, voiceprints, etc. Iris recognition is currently recognized as the most stable and non-invasive biometric technology, and has been widely used in many fields such as e-commerce, access control and time attendance. In the past few decades, iris recognition technology has made great breakthroughs both in theory and application. In terms of feature extraction of iris, Daugman proposed to use Gabor filter to filter iris image and encode according to phase response; Boles proposed to use wavelet zero-crossing detection and correlation analysis method to extract features of iris image; Wilde...

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
CPCG06V40/197G06V40/18
Inventor 吴宪祥叶素华郭宝龙王娟杨强呼香艳韩宗亭李星星陈晨
Owner XIDIAN 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