Accurate age detection is a crucial aspect in various sectors including security, marketing, and demographic analysis, where understanding the age of individuals can lead to better service delivery and enhanced user experience. This study explores the enhancement of age detection algorithms using Convolutional Neural Networks (CNNs). Leveraging a unique combination of the UTKFace and Facial-age datasets, our approach introduces an advanced data augmentation and balancing technique. This methodological innovation significantly contributes to optimizing CNN performance in age detection tasks. The proposed technique not only overcomes the common challenges in age estimation but also achieves an accuracy of 90.51%, and a noteworthy F1 score of 89.82%, which demonstrates the model’s accuracy and robustness. The findings of this research hold substantial implications for improving age detection processes, offering a promising direction for future applications in various fields that require reliable age estimation.