Development of a Fingerprint-Based Gender Detection System Using an Optimized Convolutional Neural Network

Abstract

Biometrics is a technology that identifies or verifies individuals based on unique physical or behavioral traits, offering a reliable form of authentication in sectors like healthcare, law enforcement, and security. Existing gender detection systems using fingerprints face challenges due to poor image quality and complex ridge patterns, while Convolutional Neural Networks (CNNs), though promising, are hindered by issues like overfitting, slow convergence, and getting trapped in local minima. Therefore, this study developed a fingerprint-based gender detection system through the optimization of CNN with Whale Optimization Algorithm. A dataset of 2,200 gender-labelled fingerprint images (1,320 male and 880 female) was acquired from Kaggle.com. The images underwent preprocessing involving cropping, grayscale conversion, histogram equalization for enhancement, and edge detection filtering to eliminate noise. Optimized CNN model was formulated using Whale Optimization Algorithm (WOA) by tuning CNN hyperparameters: number of neurons and dropout rate. The resulting WOA-CNN was employed for feature extraction (edges, texture patterns, shapes) and detection of fingerprint images. The model was implemented in MATLAB R2023a. Performance was evaluated using accuracy, sensitivity, specificity, false positive rate, precision, and recognition time, with an 80-20% training-testing split. CNN achieved 95.86% accuracy, 96.44% sensitivity, 95.00% specificity, 5.00% false positive rate, 96.66% precision, and 99.90 s recognition time. WOA-CNN achieved 97.23% accuracy, 97.58% sensitivity, 96.70% specificity, 3.30% false positive rate, 97.80% precision, and 87.40 s recognition time. This research showed WOA-CNN outperformed CNN in all metrics. It is recommended for use in biometric authentication, security checkpoints, and forensic investigations.