Gait is known to be an effective behavioral biometric trait for the identification of individuals. However, clothing has a dramatic influence on the recognition rate. Researchers have attempted to deal with this issue of clothing by segmenting parts of the gait images based on anatomical proportions. However, the clothing proportion is not the same as the anatomical proportion, as clothing is designed according to the golden ratio to enhance its look. Hence, methods for eliminating the influence of clothing should be based on the proportions of clothing. In this paper, we propose the golden ratio-based segmentation method to reduce the influence of clothing. Experiments are conducted on the CASIA-B dataset, and experimental results show that the proposed method outperforms other approaches, achieving a 94.76 % recognition rate in various clothing conditions and a rate of 91.53 % when bags are being carried.