An Improved Biometric Fusion System of Fingerprint and Face using Whale Optimization

Kumar, T. Ananth; Bhushan, S.; Jangra, Surender

doi:10.14569/ijacsa.2021.0120176

Cited by 20 publications

(11 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In Table 5, it is shown that the accuracy of the proposed method is better than Mwaura et al ( 2017), Somashekhar and Nijagunarya (2018) as well as Alazawi et al (2019). The result of the proposed method is slightly lower than Aleem et al (2020), Kumar et al (2021), andPawar et al (2021) because of the two samples: sample 7 and sample 18, as shown in Table 4. Overall, the result of the proposed method is comparable to Aleem et al (2020), Kumar et al (2021) and Pawar et al (2021).…”

Section: Methods Applied Accuracymentioning

confidence: 82%

“…The result of the proposed method is slightly lower than Aleem et al (2020), Kumar et al (2021), andPawar et al (2021) because of the two samples: sample 7 and sample 18, as shown in Table 4. Overall, the result of the proposed method is comparable to Aleem et al (2020), Kumar et al (2021) and Pawar et al (2021). As mentioned in the previous section, match score level fusion contains the richest information for all input data, less noise, and is relatively easy to implement.…”

Section: Methods Applied Accuracymentioning

confidence: 91%

“…The recognition rate is based on the average of the recognition rate of face and fingerprint. The result of the proposed method is slightly lower than Aleem et al (2020), Kumar et al (2021), andPawar et al (2021) because of the two samples: sample 7 and sample 18, as shown in Table 4. Overall, the proposed method is comparable to those baseline approaches.…”

Section: Conclusion and Recommendationsmentioning

confidence: 91%

“…It also includes the wealthiest information about the input pattern compared to feature-level fusion. Both Kumar et al (2021), andPawar et al (2021) are using feature-level fusion, where in most cases, feature-level fusion is hard to execute when the size of the features is not the same. In most conditions, the relationship between all features is not known in advance, noisy and redundant.…”

Section: Methods Applied Accuracymentioning

confidence: 99%

“…Recently, Kumar et al (2021) proposed an improved biometrics system based on face and fingerprint. Whale optimization is adopted with minutiae feature for fingerprint recognition and Maximally Stable External Regions (MSER) for face recognition.…”

Section: Related Workmentioning

confidence: 99%

See 4 more Smart Citations

Person Verification Based on Multimodal Biometric Recognition

Joseph¹,

Lian²,

Kipli³

et al. 2021

JST

View full text Add to dashboard Cite

Nowadays, person recognition has received significant attention due to broad applications in the security system. However, most person recognition systems are implemented based on unimodal biometrics such as face recognition or voice recognition. Biometric systems that adopted unimodal have limitations, mainly when the data contains outliers and corrupted datasets. Multimodal biometric systems grab researchers’ consideration due to their superiority, such as better security than the unimodal biometric system and outstanding recognition efficiency. Therefore, the multimodal biometric system based on face and fingerprint recognition is developed in this paper. First, the multimodal biometric person recognition system is developed based on Convolutional Neural Network (CNN) and ORB (Oriented FAST and Rotated BRIEF) algorithm. Next, two features are fused by using match score level fusion based on Weighted Sum-Rule. The verification process is matched if the fusion score is greater than the pre-set threshold. The algorithm is extensively evaluated on UCI Machine Learning Repository Database datasets, including one real dataset with state-of-the-art approaches. The proposed method achieves a promising result in the person recognition system.

show abstract