Deep Learning Ensemble Approach to Age Group Classification Based On Fingerprint Pattern

Abstract

The age distribution of a population is extremely valuable to any business or country. In order to make decisions with regard to facility allocations and other social economic developmental issues, determination of age group distribution information is essential. The attempt to deceive others about one's age is a significant problem in the sporting world, as well as in other organizations and electoral processes. Therefore, there is a requirement for an age detection system, which is required to authenticate individual claims. Fingerprint-based age estimate research is scarce due to paucity of dataset. However, there are indications that fingerprints can reveal age demographic. This study's objective is to live-scan fingerprint images in order to identify age groups. This study proposed novel Dynamic Horizontal Voting Ensemble (DHVE) with Hybrid of Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) as the base learner. The method constructs a horizontal voting ensemble for prediction by dynamically determining proficient models based on the validation accuracy metric during base learner training on the training set. Accuracy, recall, precision, and the F1 score were employed as standard performance metrics to measures the model's performance analysis. According to this study, predicting individual age group was accurate to a degree of above 91%. The DHVE network performed well due to the design of the layers. Integration of dynamic selection approach to horizontal voting ensemble improved the average performance of the model output.