Person identification from fingernails and knuckles images using deep learning features and the Bray-Curtis similarity measure

Alghamdi, Mona; Angelov, Plamen; Pellicer, Alvaro Lopez

doi:10.1016/j.neucom.2022.09.123

Cited by 6 publications

(3 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The choice of this model resulted from many evaluations applied to various deep learning models and showed outstanding performance. Therefore, we retrained the DenseNet201 and utilised the same structure suggested in this study [15]. The very first 700 layers of DenseNet201's initial model were frozen.…”

Section: B Retraining Deep Learning For Extracting Featuresmentioning

confidence: 99%

See 1 more Smart Citation

A Multi-modal Biometric Approach Based on Score-level Fusion and Fine-tuning Deep Learning Features

Alghamdi

2022

2022 IEEE 11th International Conference on Intelligent Systems (IS)

Self Cite

View full text Add to dashboard Cite

This paper presents a multimodal biometric approach applied to all fingernails and knuckle creases of the five human fingers for identifying persons. In this paper, the proposed biometric technique consists of several phases. The method starts with the detection and localisation of the main components of the hand, defining the region of interest (ROI), segmentation, feature extraction by retraining the DenseNet201 model, measuring the similarity using different metrics, and lastly, improving the person identification performance by implementing score-level fusion. This approach presents different methods for person identification, which combine fingernails, knuckles based on the modality type, and whole hands based on different similarity metrics. This paper uses various similarity metrics to distinguish between individuals. These include the Bray-Curtis, Cosine, and Euclidean metrics. Two main score-level fusion techniques are employed: the majority voting (MV) and weighted average (WA). The experimental results are evaluated with well-known databases, the '11k Hands' and the Hong Kong Polytechnic University Contactless Hand Dorsal Images 'PolyU', show the proposed algorithm's efficiency. Using the MV on the Bray-Curtis similarity measure, the fingernail-based and the base-knucklebased fusion obtained 100% in the identification estimation. In addition, the identification rate gained 100% in regions of hands and whole hands from the two popular datasets exceeded the performance of the state-of-the-art approaches.

show abstract

Section: B Retraining Deep Learning For Extracting Featuresmentioning

confidence: 99%

“…The learning strategy was stochastic gradient descent, with a learning rate of 0.001, a Nesterov momentum of 0.9, and a loss function of categorical cross-entropy. Finally, after 100 epochs, the model was trained with all its layers and parameters [15].…”

Section: B Retraining Deep Learning For Extracting Featuresmentioning

confidence: 99%

A Multi-modal Biometric Approach Based on Score-level Fusion and Fine-tuning Deep Learning Features

Alghamdi

2022

2022 IEEE 11th International Conference on Intelligent Systems (IS)

Self Cite

View full text Add to dashboard Cite

show abstract

“…In 2013, Alghamdi et al [15] proposed a new way to combine the features of the nails and the fingers joints simultaneously, as joint biometrics were combined with other biometrics of the fingers, which are unique features of each person. This work was done by relying on an algorithm to extract ROI from joints and nails simultaneously, as four fingers of the same hand were relied upon, and the thumb was neglected.…”

Section: Introductionmentioning

confidence: 99%

A new approach to develop biometric fingerprint using human right thumb fingernail

Al-Sultan

Alhialy

Alkhaled

et al. 2023

IJEECS

View full text Add to dashboard Cite

In this article, we analyzed the structure of human nails to develop a modern biometric authentication system based on the nail bed and finger lunula. The results of the studies on the collected images proved that each fingernail has distinctive characteristics in terms of the length and width of the nail and the lunula, even identical twins. We focused on the fingernail of the right thumb because of its large size and the accuracy and clarity of the nail. The mediation of the indicative points on the nail bed and on the lunula was used to form the pentagonal structure and use it as a region of interest. Then an ensemble independent component analysis, principal component analysis, haar wavelet, and scale invariant feature transformation, were used. Later we classified these algorithms using support vector machine and Naive Bayes techniques, the performance of each algorithm was analyzed by feature extraction with two classifiers. This study was conducted on 100 participants and showed that this new method could be used as a biometric identification system for humans. There was no similarity in results for all verified samples.

show abstract

Face and Iris Recognition Using Neural Network: A Review

Rani,

Mohan,

Kaushal

2023

2023 3rd International Conference on Innovative Sustainable Computational Technologies (CISCT)

View full text Add to dashboard Cite

Person identification from fingernails and knuckles images using deep learning features and the Bray-Curtis similarity measure

Cited by 6 publications

References 32 publications

A Multi-modal Biometric Approach Based on Score-level Fusion and Fine-tuning Deep Learning Features

A Multi-modal Biometric Approach Based on Score-level Fusion and Fine-tuning Deep Learning Features

A new approach to develop biometric fingerprint using human right thumb fingernail

Face and Iris Recognition Using Neural Network: A Review

Contact Info

Product

Resources

About