An artificial intelligence based multimodal biometric recognition using Fully Convolutional Residual Neural Network
|
Full Text |
Pdf
|
|
Author |
K. Sharada
|
|
e-ISSN |
1819-6608 |
|
On Pages
|
2216-2230
|
|
Volume No. |
18
|
|
Issue No. |
19
|
|
Issue Date |
December 11, 2023
|
|
DOI |
https://doi.org/10.59018/1023272
|
|
Keywords |
multimodal biometric recognition system, analysis, fully convolutional residual neural network, principal component, particle swarm optimization.
|
Abstract
The protection of biometric information is rapidly becoming an increasingly significant challenge in the field of data security. In recent years, there has been a precipitous growth in the number of research endeavours being performed in biometrics. This surge in research endeavours has been driven by a growing interest in the discipline. It is still difficult to solve the problem of developing a multimodal biometric system (MBS) with improved accuracy and recognition rate for use in smart cities. The numerous works have all used MBSs, which has led to a reduction in the security criteria that are required. Because of this, the major focus of this study is centred on the creation of a multimodal biometric recognition system (MBRS) via the utilisation of deep learning Fully Convolutional Residual Neural Network (FCRN) classification. A Gaussian filter is first applied to the images obtained from the ear, face, fingerprint, iris, and palmprint databases. This step is performed at the very beginning of the process. This causes the photos to go through pre-processing, which gets rid of the many kinds of noise that were presented. In addition, the grey level co-occurrence matrix, also known as the GLCM, is used to derive the multimodal properties. Following that, Particle Swarm Optimization (PSO) and Principal Component Analysis (PCA) are utilized so that the total number of features can be reduced to the smallest possible amount. The PSO is utilised so that features can be picked and selects the characteristics from the available set that are the most helpful. Finally, the FCRN classifier is used so that the biometric recognition technique can be carried out by using the training PSO features from the test dataset. In conclusion, the findings of the simulation reveal that the implementation of the suggested MBRS-FCRN led to a reduction in losses and an improvement in accuracy in comparison to previous approaches. The proposed MBRS-FCRN achieved an accuracy of 98.179%, sensitivity of 98.346%, and specificity of 98.186% compared to existing methods.
Back