A Novel Convolutional Neural Network Architecture for Enhanced Gait Recognition using Gait Energy Images

DOI

10.2991/978-94-6463-738-0_65How to use a DOI?

Keywords

Gait Recognition; GEI; CASIA Gait Database; CNN

Abstract

Gait recognition is a modern form of biometric identification that utilizes the walking mannerisms of a specific person. Compared to conventional biometrics, gait recognition has low intrusion and can work with identification from a distance, and that is why it is applicable in fields like surveillance, security, and forensics. This paper proposes a new model for gait recognition using CNN based on the Gait Energy Images (GEIs) from the CASIA Gait Database. Several factors in Casia, such as multiple viewing points, make the models developed from it more accurate. Our recommended CNN model has a level of accuracy of 96%, which is even higher than pretrained CNNs like DenseNet, MobileNet, and Xception Net. This article discusses earlier work carried out on gait recognition, provides brief information and examples on the CASIA dataset as well as the structure of the GEIs, and discusses the proposed CNN model, the training method used to train the model, and finally compares the result achieved by the proposed model with that of the trained models. This proved to have a high effect on the alteration of the recognition of manner; this proves that the recommended method in this work is effective.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Monika Jhapate
AU  - Hemang Shrivastava
AU  - Arun Kumar Jhapate
AU  - Rajesh Kumar Nagar
PY  - 2025
DA  - 2025/06/22
TI  - A Novel Convolutional Neural Network Architecture for Enhanced Gait Recognition using Gait Energy Images
BT  - Proceedings of the International Conference on Advances and Applications in Artificial Intelligence (ICAAAI 2025)
PB  - Atlantis Press
SP  - 834
EP  - 848
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-738-0_65
DO  - 10.2991/978-94-6463-738-0_65
ID  - Jhapate2025
ER  -