DEEP HASHING FOR SECURE MULTIMODAL BIOMETRICS

Authors

  • Usha Mahadev Biradar Author
  • Prof .Gayatri Mugli Author

DOI:

https://doie.org/10.5281/haa27w62

Keywords:

IOT, Smart-Health,,

Abstract

A multi-biometric method was employed to improve the accuracy of the 
authentication process while simultaneously lowering mistake rates. Many systems, such as 
access control, PC login, e-commerce, and so on, need person identity. The biometric system 
is most likely utilized for security. The two frameworks of biometric systems are unimodal 
biometric and multimodal biometric. 
In a unimodal system, a single biometric feature is employed, while a multimodal system uses 
many biometric traits. 
In comparison to a single-modal biometric framework, a multimodal biometric framework is 
more exact. This proposed study will address the many types of biometric systems, such as 
unimodal and multimodal systems. Discuss the comparability of several prior modalities in 
biometric systems and their comparative analysis. A multi-modal system is used to compare 
receptive techniques. The need for biometric systems is increasing on a daily basis. The 
disadvantages of the unimodal system are also shown, which explains why the need for 
multimodal transportation will expand. During this analytical task, we will mostly analyze 
earlier work that is unimodal and multimodal. Two features, such as fingerprints and iris scans, 
are merged in the proposed multi biometric system. The suggested system is evaluated using a 
standard database. Various characteristics are extracted from each trait using various feature 
extraction methods. 
The matching score of these extracted characteristics is determined independently. The 
weighted fusion approach is used to integrate these separate scores. According to the 
observations, 96% accuracy is attained, overcoming the constraints of the current method. 

,

References

Purohit Ali, Himanshu Ali, and Pawan K. Ajmera. "Optimal feature level fusion for secure

human authentication in multimodal biometric system." 1-12 in Machine Vision and

Applications 32, no. 1 (2021).

Mehwish Leghari, Shahzad Memon, Lachhman Das Dhomeja, Akhtar Hussain Jalbani, and

Asghar Ali Chandio, "Deep Feature Fusion of Fingerprint and Online Signature for Multimodal

Biometrics," Computers 10, no. 2 (2021), p. 21.

Vincenzo Conti, Leonardo Rundo, Carmelo Militello, Valerio Mario Salerno, Salvatore

Vitabile, and Sabato Marco Siniscalchi. IET Biometrics, vol. 10, no. 1 (2021), pp. 44-64.

S. A. Kalaiselvan, S. U. Aswathy, R. Radhakrishnan, and A. R. Shamna. Journal of Ambient

Intelligence and Humanized Computing (2020): 1-9. "A multimodal biometric authentication

scheme based on feature fusion for improving security in cloud environments."

"Multimodal Biometric System Iris and Fingerprint Recognition Based on Fusion Technique,"

Mustafa, Ahmed Shamil, Aymen Jalil Abdulelah, and Abdullah Khalid Ahmed. 7423-7432 in

International Journal of Advanced Science and Technology 29 (2020).

Downloads.

Published

2023-03-15

Issue

Section

Articles

How to Cite

DEEP HASHING FOR SECURE MULTIMODAL BIOMETRICS . (2023). Phoenix: International Multidisciplinary Research Journal ( Peer Reviewed High Impact Journal ), 1(2), 104-108. https://doi.org/10.5281/haa27w62