Ateb-Gabor Filtering Method in Fingerprint Recognition

Nazarkevych, Mariya; Nazarkevych, Hanna; ml., Vincent Karovic

doi:10.1016/j.procs.2019.09.440

Cited by 5 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The classifier continuously adjusts parameters according to the input data and its classification labels to achieve higher classification accuracy and stronger robustness. The features extracted from fingerprint images for classification can be subdivided into: field distribution [5]- [7] such as orientation field, gradient field, and frequency field; texture structure [8]- [10] such as ridge line flow; filter response [11]- [13] such as Gabor and wavelet filter responses; and minutiae topology structure [7], [10], especially singularity point distribution. Common powerful non-NN classifiers mainly include SVM (Support Vector Machine) [7], [10], [12], KNN (K Nearest Neighbor) [10], [11], Naive Bayes [12], etc.…”

Section: Introductionmentioning

confidence: 99%

Lightweight Convolutional Neural Network Based on Singularity ROI for Fingerprint Classification

Wen

Zhou

2020

IEEE Access

View full text Add to dashboard Cite

Fingerprint classification is a significant guarantee for efficient and accurate fingerprint recognition, especially when dealing with one-to-many fingerprint recognition. However, due to large intra-class variability, small inter-class variability, and noise, existing fingerprint classification algorithms still require further improvement in performance and efficiency. In this paper, a Lightweight CNN (Convolutional Neural Network) structure based on singularity ROI (region of interest) is proposed. The experimental results show that the accuracy on testing set of the proposed structure achieves 93%, which is far better than classic non-NN (neural network) classifiers, including RF(Random Forest), KNN (K-Nearest-Neighbor), LR (Logistic Regression), Linear SVM (Support Vector Machine), and RBF (Radial Basis Function) SVM. More momentously, compared with other three CNN structures published in recent years, the proposed structure achieves similar or even better performance with 1/12 to 1/38 parameter scale of other structures, which helps to proceed faster training and testing. Moreover, the proposed CNN model with fewer neurons can achieve better suppression of overfitting and robustness to noise.

show abstract