Abstract. This study presents a potential methodology for the identification of individuals based on their gait patterns, even when they are wearing different attire. The approach described in this study utilizes modified local patterns that have been specifically designed to be robust to rotation. These patterns enable the extraction of more discerning characteristics, particularly in scenarios where individuals may be wearing diverse clothing. The procedure was outlined in a comprehensive manner, including explanations for each step of the process. The experiments provided confirmation of the notable efficiency of gait-based person identification in scenarios where individuals wear varying attire. Keywords: Surveillance systems, Human identification, Silhouette extraction, Gait Energy Image, classification, Local Binary Pattern, Gait recognition.