Deep rule-based classifier for finger knuckle pattern recognition system

Attia, Abdelouahab; Akhtar, Zahid; Chalabi, Nour Elhouda; Maza, Sofiane; Chahir, Youssef

doi:10.1007/s12530-020-09359-w

Cited by 17 publications

(10 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Attia et al [9] proposed technique, for the information finger knuckle, two sorts of elements (i.e., binarized factual picture elements and gabor filer bank) are extricated, which are then taken care of to fluffy principles-based multi-facet profound rule classifier to decide if the client is real or faker. Morales et al [10] applied a Gabor channel to improve the FKP data and a scale-invariant component change (filter) to extricate the elements.…”

Section: -Related Workmentioning

confidence: 99%

Finger knuckle pattern person identification system based on LDP-NPE and machine learning methods

Al-juboori

Abed

2022

Bulletin EEI

View full text Add to dashboard Cite

Biometric-based individual distinguishing proof is a successful strategy for consequently perceiving, with high certainty, an individual's character. The utilization of finger knuckle pictures for individual ID has shown promising outcomes and produced a ton of interest in biometrics. By seeing that the surface example delivered by twisting the finger knuckle is profoundly particular, in this paper we present a new biometric validation framework utilizing finger-knuckle-print (FKP) imaging. In this paper, another methodology in view of neighborhood surface examples is proposed. Local derivative pattern (LDP) histogram is investigated for FKP description. Then based on neighborhood preserving embedding (NPE) is used for dimension reduction to the feature vector. The feature extraction method is computed and evaluated in the identification framework task. The machine learning methods (multiclass support vector machine (MSVM), random forest (RF), k-nearest neighbor (KNN)) are proposed for classification. The system is tested on the PolyU finger knuckle database. The empirical results proved that the proposed model has the best results with RF. Moreover, our proposed LDP-NPE model has been evaluated and the results show remarkable efficiency in comparison with previous work. Experimentally, the proposed model has better accuracy as reflected by 99.65%.

show abstract

Section: -Related Workmentioning

confidence: 99%

Finger knuckle pattern person identification system based on LDP-NPE and machine learning methods

Al-juboori

Abed

2022

Bulletin EEI

View full text Add to dashboard Cite

show abstract

“…These systems improve the accuracy and efficiency of any identification or verification task [1]. This work [7] investigated a local textural descriptor as a binarized statistical image feature (BSIF). This feature descriptor essentially employs a series of fixed-size filters to represent the neighbourhood layout of the core pixel.…”

Section: Literaturementioning

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)

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

“…Then, the genetic algorithm was used to extract the optimized sub-features. Attia et al [25] LeCun and Bengio [27] were the first to propose CNN architecture. CNN models have been the subject of considerable attention in most computer vision applications [28][29][30][31].…”

Section: Literature Reviewmentioning

confidence: 99%

Deep Convolutional Neural Network for Finger-Knuckle-Print Recognition

Zohrevand

Imani

Ezoji

2021

IJE

View full text Add to dashboard Cite

Finger-Knuckle-Print (FKP) is an accurate and reliable biometric in compare to other hand-based biometrics like fingerprint because of the finger's dorsal region is not exposed to surfaces. In this paper, a simple end-to-end method based on Convolutional Neural Network (CNN) is proposed for FKP recognition. The proposed model is composed only of three convolutional layers and two fully connected layers. The number of trainable parameters hereby has significantly reduced. Additionally, a straightforward method is utilized for data augmentation in this paper. The performance of the proposed network is evaluated on Poly-U FKP dataset based on 10-fold cross-validation. The best recognition accuracy, mean accuracy and standard deviation are 99.83%, 99.18%, and 0.76, respectively. Experimental results show that the proposed method outperforms the state-of-the-arts in terms of recognition accuracy and the number of trainable parameters. Also, in compare to four fine-tuned CNN models including AlexNet, VGG16, ResNet34, and GoogleNet, the proposed simple method achieved higher performance in terms of recognition accuracy and the numbers of trainable parameters and training time.

show abstract

Deep rule-based classifier for finger knuckle pattern recognition system

Cited by 17 publications

References 36 publications

Finger knuckle pattern person identification system based on LDP-NPE and machine learning methods

Finger knuckle pattern person identification system based on LDP-NPE and machine learning methods

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

Deep Convolutional Neural Network for Finger-Knuckle-Print Recognition

Contact Info

Product

Resources

About