The field of Human Gait Recognition (HGR) leverages unique walking patterns for non-invasive, discreet biometric identification. This study highlights the importance of comprehensive datasets in the development, testing, and validation of HGR algorithms. While current datasets, such as those from Carnegie Mellon University Motion of Body (CMU MoBo), Southampton (SOTON), Chinese Academic of Science Institute of Automation (CASIA B), and Osaka University Institute of Scientific Industrial Research (OU-ISIR), have advanced in scale and complexity, they often lack diversity and comprehensive sample representation. To address this gap, we introduce the TecNM Gait-DS dataset (Tecnologico Nacional de Mexico), specifically designed for Latin American populations, featuring 13 viewing angles and five walking variations. Utilizing a Self-Supervised Vision Transformer DINO (Deeper Into Neural Networks) model for view angle classification, our evaluation demonstrates significant improvements in classification accuracy. This dataset not only enhances sample diversity but also supports the development of more robust HGR systems. Our results underscore the potential for improved accuracy and ethical considerations in HGR, advocating for ongoing refinement of datasets to achieve optimal performance and societal acceptance.