This work addresses the challenge of verifying familial relationships through facial features, a task often complicated by age-related variations. Traditional kinship verification models struggle to account for these changes, leading to reduced accuracy. However, accurate kinship verification is essential for a variety of applications, including forensic investigations, family reunification, and social media analysis. To address this issue, the objective of the study was to enhance Kinship Verification by integrating age transformation techniques into a Deep Learning framework. The proposed approach employed the Learnable Age Transformation Synthesis (LATS) algorithm to transform facial images across different age ranges, thereby making familial traits more discernible. A Deep Learning model based on a Siamese Network Architecture was trained using the Families in the Wild (FIW) dataset, with age transformations applied at 5, 15, and 30 years to evaluate its performance in identifying mother-child and father-child relationships. The model was assessed using accuracy, F1-score, and Mean Squared Error (MSE) across the different transformation scenarios. Results demonstrated an overall accuracy of 0.87, with the best performance observed in father-child pairs at the 5-year transformation and in mother-child pairs at the 15-year transformation. These findings highlight the model’s effectiveness in capturing age-specific familial traits and underscore the value of age transformation in improving Kinship Verification accuracy.