An Improved Gait Recognition Method Using Modified Gait Energy Image

An Improved Gait Recognition Method Using Modified Gait Energy Image

gait recognition;MGEI; view detection;principal component analysis;linear discriminate analysis

Gait recognition is a valuable technology for remote and concealed identity authentication, widely applied in intelligent video monitoring. Existing gait recognition algorithms fall into two categories: appearance-based methods and model-based methods. While gait features differ from static biometric features like faces or fingerprints, they exhibit significant and robust characteristics over a gait cycle. Gait Energy Image (GEI) is a commonly used feature in gait recognition, synthesizing gait images into a single representative image. In this study, we propose an improved gait recognition method that addresses the impact of viewpoint variations, clothing, and carried objects. The method uses modified GEI (MGEI) and view detection and combins two-dimensional principal component analysis and linear discriminant analysis for feature extraction. Experimental results demonstrate the effectiveness of the proposed method in reducing the influence of view variations and achieving robust gait recognition.

Jing Li

www.ijcit.com

March 2024

PERI IRAWAN

PDF

ENGLISH

TEXT