Dynamic Horizontal Voting Ensemble Deep Learning Approach to Combined Classification for Human Age, Gender and Ethnicity Soft Biometric Using Fingerprint Pattern

Abstract

There is paucity of information regarding the probability that fingerprints may reveal combined soft biometric trait of human age, gender, and ethnicity. This challenge is due to lack of data. This has however, prompted academics to conduct their demographic classification-related work using the limited fingerprint dataset that is now available. However, complete fingerprint datasets collected under conventional and real-world conditions are not easily available for research reasons. This research aims to design a multi-task Deep Learning model for classifying the combined traits of ethnicity, gender, and age group estimation using fingerprint pattern. The fingerprint database was collected using a live scan method in real-world conditions, with subjects from three most numerous racial groups of Nigeria which are Yoruba, Igbo and Hausa, with consideration of the subject gender and age groups. The proposed method for the fingerprint image classification and training is the novel Dynamic Horizontal Voting Ensemble (DHVE) with Hybrid of Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) being utilized as the base (weak) learner. The dynamic selection method was utilized to determine classifiers in the normal horizontal voting ensemble, hence enhancing the ensemble technique's average accuracy. Standard performance classification metric inclusive of Accuracy, hold in thoughts, Precision, and F1 rating had been implemented to evaluate the model's performance. The result shows 76% accuracy in predicting person’s combined age group, ethnicity and gender. We also compared its performance against other approaches. It outperforms other cutting-edge algorithm like the CNN model in terms of performance metrics.