<![CDATA[This research aims to design and implement an age detection application based on facial images using a deep learning approach with a Convolutional Neural Network (CNN) architecture. The model is built to recognize and extract facial features in order to estimate an individual’s age automatically. Facial image datasets were obtained from public sources and enhanced through augmentation techniques such as rotation, flipping, and lighting adjustment to increase data variability. The training process involved splitting the data into training, validation, and testing sets. The model was evaluated using accuracy, precision, recall, and F1-score metrics. The gender detection system achieved an accuracy of 82.99% with a precision of 80.95% for males and 84.47% for females. Recall scores were 85.15% for males and 80.12% for females. For age detection, precision, recall, and F1-score varied across different age groups. Overall, the model demonstrates exemplary performance in age prediction, though it still faces challenges in distinguishing closely spaced age categories.]]>
Copyrights © 2025
