Finger vein identification using deeply-fused Convolutional Neural Network

Ismail, Boucherit; Zmirli, Mohamed Ould; Hamza, Hentabli; Rosdi, Bakhtiar Affendi

doi:10.1016/j.jksuci.2020.04.002

Cited by 53 publications

(47 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 3 illustrates two previous studies that used the SDUMLA-HMT dataset for building a deep learning model for finger vein identification. The finger vein unimodal model in [ 20 ] gave a recognition rate of 99.48%, which has exceeded our model. This result may be attributed to the fact that the model in [ 20 ] uses multiple instances of finger vein rather than one instance as we do in our study.…”

Section: Discussion Of Resultsmentioning

confidence: 59%

“…The finger vein unimodal model in [ 20 ] gave a recognition rate of 99.48%, which has exceeded our model. This result may be attributed to the fact that the model in [ 20 ] uses multiple instances of finger vein rather than one instance as we do in our study. The model [ 20 ] takes five images of finger vein and this makes the chance for identifying the person higher than using only one finger vein instance.…”

Section: Discussion Of Resultsmentioning

confidence: 59%

“…The model was trained using the SDUMLA dataset, and it obtained an accuracy rate of 99.53%. Recently, Boucherit et al [ 20 ] used finger vein traits to build an identification model, developing a merge CNN model that used several identical CNNs with different input image qualities. The authors conducted different experiments using different network parameters and layers.…”

Section: Related Workmentioning

confidence: 99%

“…However, these deep learning-based approaches, while effective, are very computationally expensive and time consuming [ 11 , 12 , 13 , 14 , 15 , 16 , 17 , 18 , 19 , 20 ]. In addition, studies deploying deep learning algorithms in multimodal biometric systems [ 13 , 14 , 15 , 16 , 17 , 18 , 19 , 20 ] begin the experimentation process by applying region detection methods prior to entering data into deep learning model. The use of region detection methods requires first selecting a suitable technique for a particular trait, also, the process can be time-consuming [ 1 ].…”

Section: Related Workmentioning

confidence: 99%

“…Recently, deep learning has made a considerable impact and produced excellent results in biometrics systems [ 11 , 12 , 13 , 14 , 15 , 16 , 17 , 18 , 19 , 20 ]. The deep learning algorithms have overcome many of the limitations of other machine learning algorithms, particularly those associated with feature extraction techniques.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Deep Learning Approach for Multimodal Biometric Recognition System Based on Fusion of Iris, Face, and Finger Vein Traits

Alay¹,

Al-Baity

2020

Sensors

114

View full text Add to dashboard Cite

With the increasing demand for information security and security regulations all over the world, biometric recognition technology has been widely used in our everyday life. In this regard, multimodal biometrics technology has gained interest and became popular due to its ability to overcome a number of significant limitations of unimodal biometric systems. In this paper, a new multimodal biometric human identification system is proposed, which is based on a deep learning algorithm for recognizing humans using biometric modalities of iris, face, and finger vein. The structure of the system is based on convolutional neural networks (CNNs) which extract features and classify images by softmax classifier. To develop the system, three CNN models were combined; one for iris, one for face, and one for finger vein. In order to build the CNN model, the famous pertained model VGG-16 was used, the Adam optimization method was applied and categorical cross-entropy was used as a loss function. Some techniques to avoid overfitting were applied, such as image augmentation and dropout techniques. For fusing the CNN models, different fusion approaches were employed to explore the influence of fusion approaches on recognition performance, therefore, feature and score level fusion approaches were applied. The performance of the proposed system was empirically evaluated by conducting several experiments on the SDUMLA-HMT dataset, which is a multimodal biometrics dataset. The obtained results demonstrated that using three biometric traits in biometric identification systems obtained better results than using two or one biometric traits. The results also showed that our approach comfortably outperformed other state-of-the-art methods by achieving an accuracy of 99.39%, with a feature level fusion approach and an accuracy of 100% with different methods of score level fusion.

show abstract

Section: Discussion Of Resultsmentioning

confidence: 59%

Section: Discussion Of Resultsmentioning

confidence: 59%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Deep Learning Approach for Multimodal Biometric Recognition System Based on Fusion of Iris, Face, and Finger Vein Traits

Alay¹,

Al-Baity

2020

Sensors

114

View full text Add to dashboard Cite

show abstract

A secure finger vein verification and authentication scheme for banking network

D¹,

Dhanapal

2022

Concurrency and Computation

View full text Add to dashboard Cite

SummaryThe development of electronic exchanges has created a more important interest in fast and accurate customer IDs and verification. Structures, bank records, and PC framework often use personally identifiable access code IDs and test numbers (PINs) for reliable status. Biometric verification requires a level of security, unchanged structure, spoofing, and reliability. In this research work, a biometric authentication system was developed to provide security for access to the ATM network. Honest technology used for security purposes to provide efficient ATM network security is a finger vein. This method undergoes image processing technology such as preprocessing, feature extraction, and classification to locate the finger vein region for accessing the ATM network. Finally, the cascade neural network acts as a classifier method to differentiate registered and unregistered user. The performance analysis of this method is simulated by MATLAB and the process is evaluated to measure the efficient security of the network. The dataset is segregated into two stages; one for training and other for testing. The features extracted with the help of hidden layers with neurons. The matched finger vein is compared to check the accuracy.

show abstract

An Arcloss-Based and Openset-Test-Oriented Finger Vein Recognition System

Chen

Haohan

et al. 2021

Biometric Recognition

View full text Add to dashboard Cite

Finger vein identification using deeply-fused Convolutional Neural Network

Cited by 53 publications

References 30 publications

Deep Learning Approach for Multimodal Biometric Recognition System Based on Fusion of Iris, Face, and Finger Vein Traits

Deep Learning Approach for Multimodal Biometric Recognition System Based on Fusion of Iris, Face, and Finger Vein Traits

A secure finger vein verification and authentication scheme for banking network

An Arcloss-Based and Openset-Test-Oriented Finger Vein Recognition System

Contact Info

Product

Resources

About