A Multimodal Biometric System For Personal Verification Based On Different Level Fusion Of Iris And Face Traits

Alay, Nada; Al-Baity, Heyam H.

doi:10.21786/bbrc/12.3/3

Cited by 13 publications

(24 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our previous research [ 24 ], the images of each subject (class) in SDUMLA-HMT were divided randomly into training, validation, and testing sets using different percentages (80:10:10), (60:20:20), (90:15:5), and (70:20:10). The best results were obtained when using the percentage of (60:20:20), therefore, in this research, the data of each subject is divided into 60:20:20, 60% for the training, 20% for validation and 20% for testing.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…For the iris CNN model, the iris CNN model in our previous research [ 24 ] was used. The structure of the CNN model is the same as that of the VGG-16 model, with some modifications that were made to avoid overfitting.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…For the face CNN model, the face CNN model in our previous research [ 24 ] was used. The model is similar to VGG-16, with some additional layers.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…In [ 24 ], our previous study began with training and testing the model for each trait separately to check the effectiveness of each unimodal model before fusing them to a multimodal model. The CNN algorithm was used for feature extraction and classification.…”

Section: Proposed Methodsmentioning

confidence: 99%

“…The SDUMLA-HMT dataset was selected to evaluate the performance of the multimodal system. The multimodal biometric system in [ 24 ] achieved an accuracy rate of 99.22% using the feature-level fusion approach, and achieved an accuracy rate of 100% using the score-level fusion approach.…”

Section: Proposed Methodsmentioning

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

Self Cite

137

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: Experiments and Resultsmentioning

confidence: 99%

Section: Experiments and Resultsmentioning

confidence: 99%

“…For the face CNN model, the face CNN model in our previous research [ 24 ] was used. The model is similar to VGG-16, with some additional layers.…”

Section: Experiments and Resultsmentioning

confidence: 99%

Section: Proposed Methodsmentioning

confidence: 99%

Section: Proposed Methodsmentioning

confidence: 99%