Impact of Kernel Size on CNN-Based Fingerprint Gender Classification

Sri Suwarno (Informatics Study Program of Information Technology Faculty, Duta Wacana Christian University, Indonesia)
Joko Purwadi (Informatics Study Program of Information Technology Faculty, Duta Wacana Christian University, Indonesia)

Jurnal Teknik Informatika (JUTIF)
Vol. 7 No. 4 (2026): JUTIF Volume 7, Number 4, August 2026

This paper presents a straightforward CNN model designed to classify gender based on fingerprints. The model consists of three convolutional layers and a classification layer. To ensure computational efficiency, we select kernel sizes ranging from 3×3 to 8×8. For training, we utilized the NIST (National Institute of Standards and Technology) dataset, which includes 500 male fingerprints and 500 female fingerprints. The region of interest (ROI) for the fingerprints is set at 128×128 pixels, centered horizontally and positioned in the upper quarter vertically. To enhance image quality, we applied the CLAHE (Contrast Limited Adaptive Histogram Equalization) method. The experimental results indicate that the model achieves a validation accuracy of up to 74.176%, with an execution time of under 10 minutes. Our results indicate a potential direction for future research in the use of simple CNN architectures, despite the fact that the validation accuracy of our model is lower than that of advanced CNNs, such as ResNet or its modification, the Dense Dilated Convolution ResNet Autoencoder (DDC-ResNet), which achieves 96.5%.