Development of a Fingerprint Gender Classification Algorithm Using Fingerprint Global Features

Abdullah, Siti Fairuz; Rahman, Ahmad Fadzli Nizam Abdul; Abas, Zuraida Abal; Saad, Wira Hidayat Mohd

doi:10.14569/ijacsa.2016.070635

Cited by 3 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Berdasarkan dari penelitian ini pula metode yang digunakan sangat direkomendasikan untuk digunakan kembali apabila akan melakukan penelitian serupa yang berupa klasifikasi. [2] Penelitian untuk pengenalan error yang mungkin saja terjadi dalam pengejaan dalam Bahasa Arab. Pengenalan error terhadap pengejaan Bahasa Arab ini berfokus pada inserting, deleting, dan permutation.…”

Section: Pendahuluanunclassified

Testing The Accuracy of Fingerprint Recognition using Levenshtein Distance and Hamming Distance Methods

Ginantaka,

Saputra,

Suwarno

2023

joincs

View full text Add to dashboard Cite

The presence or evidence of attendance is crucial in monitoring the presence of every individual working in a particular field. Developing an employee attendance system using fingerprints can expedite the processing of data of employees who have or have not attended. One brand of machine used as a fingerprint attendance tool is Fingerspot Flexcode. The data obtained from the machine comes in the form of bitmap images that are converted into strings using encoding. Although the resulting string sequences are different, there is a possibility of similarity in fingerprint data among employees because the system cannot distinguish data precisely. Therefore, the comparison between the Levenshtein Distance and Hamming Distance methods is used to determine which method has the highest accuracy in processing the system's calculation. The method with the highest accuracy will determine the level of compatibility of the method with the tested tool. For example, 6 fingerprint data are taken from each of the 7 different employees, resulting in a total of 42 data as test data. The calculation results show that the accuracy of the Levenshtein Distance method is 80,76 % with a precision of 46,43 %, while the Hamming Distance method is 78,34 % with a precision of 30,50 % in processing string similarity in fingerprint data. Based on these results, it can be concluded that the Levenshtein Distance method is better in calculating similarity in fingerprint data compared to the Hamming Distance method because it has a higher level of accuracy and precision compared to the Hamming Distance method.

show abstract

Section: Pendahuluanunclassified

Testing The Accuracy of Fingerprint Recognition using Levenshtein Distance and Hamming Distance Methods

Ginantaka,

Saputra,

Suwarno

2023

joincs

View full text Add to dashboard Cite

show abstract

Comparative Study of Fingerprint-Based Gender Identification

Berriche

2022

Security and Communication Networks

View full text Add to dashboard Cite

Gender identification is a need in forensics investigation. In addition to their use for identification, fingerprints are used for gender identifications. In this work, we propose a model for fingerprint gender classification focusing on a small dataset with imbalanced classes. First, we applied denoising and equalization filters to the fingerprint images. Then, we cropped the image into a region of interest. After preprocessing the fingerprint image, we extracted fast Fourier transform (FFT) and principal component analysis (PCA) features, and we applied the min-max normalization. We train our models with each of them as well as with their fusion. To balance the initially imbalanced datasets, we used two sampling techniques: random sampling and synthetic minority oversampling Technique (SMOTE). Our comparison of the receiver operating characteristic (ROC) of K-nearest neighbours (KNN), Support Vector Machine (SVM), Decision Tree, and forward neural network showed that the best result for the area under the ROC Curve is given by the SVM classifier. Next, we compared the SVM classifier accuracy for each fingerprint position with FFT features, PCA features, and their fusion. In addition, we applied both random hybrid sampling and SMOTE sampling. We applied our method on the National Institute of Standards and Technology (NIST) special database, 4 gray scale images of fingerprint image. We showed that the fusion of FFT and PCA features gives the best gender identification accuracy when the SMOTE dataset balancing technique is applied. We found that the right ring finger was more appropriate with 75.55% of correct male gender identifications and 91.62% female gender identification. Further investigation into dataset balancing techniques will be applied in the future.

show abstract

Fingerprint Gender Classification using Univariate Decision Tree (J48)

Abdullah¹,

Rahman²,

Abas³

et al. 2016

ijacsa

Self Cite

View full text Add to dashboard Cite

Abstract-Data mining is the process of analyzing data from a different category. This data provide information and data mining will extracts a new knowledge from it and a new useful information is created. Decision tree learning is a method commonly used in data mining. The decision tree is a model of decision that looklike as a tree-like graph with nodes, branches and leaves. Each internal node denotes a test on an attribute and each branch represents the outcome of the test. The leaf node which is the last node will holds a class label. Decision tree classifies the instance and helps in making a prediction of the data used. This study focused on a J48 algorithm for classifying a gender by using fingerprint features. There are four types of features in the fingerprint that is used in this study, which is Ridge Count (RC), Ridge Density (RD), Ridge Thickness to Valley Thickness Ratio (RTVTR) and White Lines Count (WLC). Different cases have been determined to be executed with the J48 algorithm and a comparison of the knowledge gain from each test is shown. All the result of this experiment is running using Weka and the result achieve 96.28% for the classification rate.

show abstract

Development of a Fingerprint Gender Classification Algorithm Using Fingerprint Global Features

Cited by 3 publications

References 17 publications

Testing The Accuracy of Fingerprint Recognition using Levenshtein Distance and Hamming Distance Methods

Testing The Accuracy of Fingerprint Recognition using Levenshtein Distance and Hamming Distance Methods

Comparative Study of Fingerprint-Based Gender Identification

Fingerprint Gender Classification using Univariate Decision Tree (J48)

Contact Info

Product

Resources

About