<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Traditional iris recognition has high recognition accuracy and low misrecognition rate. However, in the case of mobile terminal or distance, the image resolution and image quality decrease, and the recognition rate also decreases. To solve the above problems, this article is based on deep learning technology, on the basis of single mode state recognition, from different levels of multimodal integration, the iris and the eyes in the score level fusion recognition research, put forward the adaptive dynamic weighted score fusion method, to determine the weighing values can adaptive algorithm of the modal, without artificial specified, dynamic weighting algorithm more flexible, stronger applicability. Experimental results of casIA-Iris-LAMP and CasIA-Iris-Distance Iris database in Chinese Academy of Sciences show that the proposed fusion algorithm has higher recognition accuracy and better recognition performance than the single mode recognition algorithm and the traditional fractional fusion method, which proves the effectiveness of the algorithm.</p>
</abstract>

Traditional iris recognition has high recognition accuracy and low misrecognition rate. However, in the case of mobile terminal or distance, the image resolution and image quality decrease, and the recognition rate also decreases. To solve the above problems, this article is based on deep learning technology, on the basis of single mode state recognition, from different levels of multimodal integration, the iris and the eyes in the score level fusion recognition research, put forward the adaptive dynamic weighted score fusion method, to determine the weighing values can adaptive algorithm of the modal, without artificial specified, dynamic weighting algorithm more flexible, stronger applicability. Experimental results of casIA-Iris-LAMP and CasIA-Iris-Distance Iris database in Chinese Academy of Sciences show that the proposed fusion algorithm has higher recognition accuracy and better recognition performance than the single mode recognition algorithm and the traditional fractional fusion method, which proves the effectiveness of the algorithm.

Score Level Fusion for Iris and Periocular Biometrics Recogniton Based on Deep Learning

School of Computer Science and Engineering

International Journal of Advanced Network, Monitoring and Controls

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Traditional iris recognition has high recognition accuracy and low misrecognition rate. However, in the case of mobile terminal or distance, the image...

DataSet	CASIA-Iris-Lamp	CASIA-Iris-Distance
1:9	0.968541	0.935883
2:8	0.971083	0.935883
3:7	0.976167	0.939257
4:6	0.982840	0.9392575
5:5	0.992373	0.9617547
6:4	0.990149	0.917885
7:3	0.986653	0.907761
8:2	0.983158	0.897637
9:1	0.980934	0.894263

Relevant parameters	Parameter settings
input_shape	224×224×3
batch_size	32
epoch	2000
optimizers	rmsprop
learning_rate	10⁻³
rho	0.9
decay	10-6

Hardware Environment	ProcessorGraphics card	Inter(R) XeonGold b6254Navidia GeForce RTX2080Ti
Software Environment	Operating SystemFrameworkProgramming languageCompiler	Linux Ubuntu 16.04Tensorflow-GPUPython3.6.8PyCharm

Dataset	Fusion rule	Recognition accuracy
CASIA-Iris-Lamp	Maximum value	0.992055
	Minimum value	0.955830
	Multiplication	0.992017
	Additive	0.992373
	Unimodal periocular	0.982617
	Unimodal iris	0.981252
	Adaptive weighting	0.993831

CASIA-Iris-Distance	Maximum value	0.961754
	Minimum value	0.866141
	Multiplication	0.972512
	Additive	0.961754
	Unimodal periocular	0.933633
	Unimodal iris	0.894263
	Adaptive weighting	0.985376

Dataset	Category	Iris images	Periocular images	Training set	Validation set	Test set
CASIA-Iris-Lamp	791	15820	15820	9492	3164	3164
CASIA-Iris-Distance	284	5073	5073	3160	1024	889

Score Level Fusion for Iris and Periocular Biometrics Recogniton Based on Deep Learning

Publié en ligne: 26 mai 2023

Pages: 21 - 30

DOI: https://doi.org/10.2478/ijanmc-2022-0033

Mots clés
Multimodal Fusion, Iris Recognition, Periocular Recognition, Score Level Fusion

© 2022 Yufei Wang et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figer 1.

Figer 2.

Figer 3.

Figer 4.

Figer 5.

Comparison results of different weights

Experimental configuration

Environment configuration

Comparison of experimental results

Experimental data sets

Score Level Fusion for Iris and Periocular Biometrics Recogniton Based on Deep Learning

Publié en ligne: 26 mai 2023

Pages: 21 - 30

DOI: https://doi.org/10.2478/ijanmc-2022-0033

Mots clésMultimodal Fusion, Iris Recognition, Periocular Recognition, Score Level Fusion

© 2022 Yufei Wang et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figer 1.

Figer 2.

Figer 3.

Figer 4.

Figer 5.

Comparison results of different weights

Experimental configuration

Environment configuration

Comparison of experimental results

Experimental data sets

Mots clés
Multimodal Fusion, Iris Recognition, Periocular Recognition, Score Level Fusion