A Fingerprint-Based Neural Network Approach for Age Estimation in Young Adults

Age estimation using biometric data is a critical tool in various applications, ranging from security systems to age-based access control in digital platforms. This study presents the development of a fingerprint-based age estimation system for individuals aged 15–23 years. The system captures fingerprint data using a USB-connected scanner, preprocesses the data, and utilizes a Counter-Propagation Neural Network (CPNN) trained with Grossberg's learning rule for classification. A dataset of 500 fingerprint samples was collected, and the system's performance was evaluated using metrics such as accuracy, sensitivity, and specificity across different threshold values. The system achieved a maximum accuracy of 96%, sensitivity of 94%, and specificity of 95% at a threshold of 0.7, demonstrating its effectiveness in age classification. Challenges, particularly in borderline cases, highlight the need for further refinement of the feature extraction and classification process. This study highlights the feasibility of using biometric data for age estimation, with potential applications in forensics, access control, and demographic studies. The results provide a foundation for future work on improving system performance and scalability by incorporating advanced feature extraction techniques and larger, more diverse datasets.