IIARD International Institute of Academic Research and Development

INTERNATIONAL JOURNAL OF APPLIED SCIENCES AND MATHEMATICAL THEORY (IJASMT )

E- ISSN 2489-009X
P- ISSN 2695-1908
VOL. 10 NO. 3 2024
DOI: 10.56201/ijasmt.v10.no3.2024.pg59.67

---

A Model for Authentication System Using Iris Detection in Cloud Computing

Lenu Godwin, V.I. E Anireh & Daniel matthias Email

---

Abstract

Various techniques are employed to address security concerns in the realm of cloud computing. Password authentication is widely recognised as one of the most often employed methods of authentication. Many clients choose to use easily memorable options, such as phone numbers and names, as their chosen passwords. The passwords in question possess a high degree of memorability yet are susceptible to security breaches. Consequently, the attacker possesses the capability to systematically compile a comprehensive inventory of prominent identities and numerical values, so compromising the integrity of the security measures in place. The primary aim of this paper is to develop a model for an authentication system that utilises iris detection within the context of cloud computing. The iris recognition system is comprised of two main processes, namely the registration process and the verification process. During the enrollment process, the feature vector that has been extracted is placed in the database. During the verification process, the system compared the feature set with each of the feature sets retrieved from the training image to determine the closest match with a training set image. During the process of matching, the feature that has been extracted is compared to the features that have been saved. The classification task has been performed using the Non-Symmetrical Support Vector Machine. Experiments conducted using live captured images. The findings indicate that the system operates with high efficiency and achieves a classification rate of 98% correctness.

keywords:

Authentication System, Security, Iris Detection

---

References:

[1]
Weiss, A. (2007). Computing in the Clouds. Association for Computing Machinery (ACM)


Networker, 11(4), 16–25.
[2]
Sahithi, S., Anirudh, A., Swaroop, B. and Ramya, K. R. (2019). Biometric Security for

Cloud Data using Fingerprint and Palm Print. International Journal of Innovative

Technology and Exploring Engineering (IJITEE), 8(6).
[3]
Al-hamami, A. H. and Al-juneidi, J. Y. (2015). Secure Mobile Cloud Computing Based-
On
Fingerprint, 5(2), 23–27.
[4]
Merloti, P. E. (2004). Experiment on Human Iris Recognition Using Error Back

Propagation Artificial Neural Network. Prepared for Neural Network Class (CS533) of

Spring Semester.
[5]
Rani, S. and Gangal, A. (2012). Cloud Security with Encryption using Hybrid Algorithm

and Secured Endpoints. International Journal of Computer Science and Information

Technologies, 3(3), 4302-4304.
[6]
Modi, M., Upadhaya, H. and Thakor, M. (2014). Password less authentication using

keystroke dynamics a survey. International Journal of Innovative Research in Computer

and Communication Engineering (IJIRCCE), 7060–7064.
[7]
Shekar, B. H. and Bhat, S. S. (2015). Steerable Riesz Wavelet based Approach for Iris

Recognition. IEEE Asian Conference on Pattern Recognition, 431-436.


[8]
Proença, H. and Alexandre, L. A. (2007). Toward Non-Cooperative Iris Recognition: A

Classification Approach Using Multiple Signatures. IEEE Transactions on Pattern

Analysis and Machine Intelligence, 29(4).
[9]
Provencal, H. and Alexandre, L. A. (2007). Toward Non-Cooperative Iris Recognition: A

Classification Approach Using Multiple Signatures. IEEE Trans. on Pattern Analysis

and Machine Intelligence, 29(4).
[10]
Hong-ying, G., Yue-ting, Z. and Yun-he, P. (2005). An iris recognition method based

on multi-orientation features and Non-symmetrical SVM. Journal of Zhejiang University

Science, 190-203.
[11]
Poursaberi, A. and Arrabi, B. N. (2007). Iris Recognition for Partially occluded images
Methodology and Sensitive Analysis. Hindawi Publishing corporation journal on advances
in signal processing, 12.
[12]
Ya-Ping, H., Si-Wei, L. and En-Yi, C. (2002). An Efficient Iris Recognition System.

Proceedings of the First International Conference on Machine Learning and

Cybernetics, 4-5.
[13]
Adhau, A. S. and Shedge, D (2015). Iris Recognition methods of a Blinked-Eye in Non-

Ideal Condition. IEEE International conference on Information Processing, 75-79.
[14]
Yefrenes, R., Martini, D. and Intiri, G. (2016). A Novel Approach for Iris Recognition.
IEEE Region Symposium, 231-236.
[15]
Baqar, M., Ghani, A., Aftab, A. and Yasin, S. (2016). Deep Belief Networks for Iris

Recognition based on Contour Detection. IEEE International conference on Open Source

Systems and Technologies, 72-77.

DOWNLOAD PDF

---

Back