Support Vector Machine, Multilayer Perceptron Neural Network, Bayes Net and k-Nearest Neighbor in Classifying Gender using Fingerprint Features

A scientific study of fingerprints, lines, mounts and shapes of hands are called dermatoglyphics. Dermatoglyphics features from fingerprint are statistically differ between the gender, ethnic groups, region and age categories From the previous study of gender classification in forensic area, the process of feature extraction is done manually and classify using a statistical approach. The features extracted were; ridge count (RC), ridge density (RD), ridge thickness to valley thickness ratio (RTVTR) and white lines count (WLC). The sample use consists of 300 respondents where each respondent gives 10 different fingerprints. Four classifiers which are Bayes Net, Multilayer Perceptron Neural Network (MLPNN), k-Nearest Neighbor (k-NN) and Support Vector Machine (SVM) are used in order to evaluate the performance of the proposed algorithm. The overall performance of the classifier is 95% of the classification rate. From all classifiers, SVM emerges as the best classifier for proposed algorithm.