Mathematical Formulation and Experimentation for Multi-View GEI-Based Gait Identification Using an Ensemble Learning and Optical Flow

Babita Sonare; Deepika Saxena; Vijay Katkar

doi:10.48084/etasr.17731

Authors

Babita Sonare Department of Computer Science and Engineering, Poornima University, Jaipur, Rajasthan, India
Deepika Saxena Department of Computer Science and Engineering, Poornima University, Jaipur, Rajasthan, India https://orcid.org/0000-0003-0294-1245
Vijay Katkar School of Artificial Intelligence, Bennett University, Greater Noida, India https://orcid.org/0000-0003-0858-1957

Volume: 16 | Issue: 3 | Pages: 34950-34956 | June 2026 | https://doi.org/10.48084/etasr.17731

Received: 24 January 2026 | Revised: 15 February 2026 and 3 March 2026 | Accepted: 10 March 2026 | Online: 6 May 2026

Corresponding author: Babita Sonare

Abstract

The challenge of identifying individuals in various situations, such as walking orientation and clothing conditions, from their gait patterns remains challenging in biometric recognition. To mitigate this challenge, this work presents a unified mathematical formulation that incorporates optical flow-based viewing angle estimation to reduce computational complexity and a Kernel-PCA (KPCA) ensemble framework, combining the strengths of multiple pre-trained Convolutional Neural Networks (CNNs), including EfficientB0 and B1, MobileNet and MobileNetV3 variants, as well as several RegNetX and RegNetY models. The most suitable lightweight model among pretrained CNNs is used to extract the features based on the estimated angle and Gait Energy Image (GEI) generated from the CASIA B dataset. The extracted features are refined using KPCA to improve class separability and recognition. These transformed features are utilized to train Machine Learning (ML) classifiers such as K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Random Forest, and XGBoost. From these classifiers, KNN using transformed features produced the best result. The proposed method achieved recognition accuracies between 95.6% and 99.2% across viewing angles from 0° to 180° in the training and 92.07% to 95.57% in testing. By integrating angle estimation with selective model usage, the framework significantly reduces computational overhead while maintaining high recognition performance. Collectively, the proposed approach delivers a robust and efficient solution for GEI-based person identification under a varied range of real-world conditions and viewing angles.

Keywords:

gait analysis, machine learning, convolutional neural network, ensemble, optical flow

References

E. Y. Abdullah and L. I. Jalil, "Effective stride length on load carrying capacity for ankle joint," Journal of Interdisciplinary Mathematics, vol. 24, no. 8, pp. 2345–2353, Nov. 2021.

G. Ariyanto and M. S. Nixon, "Model-based 3D gait biometrics," in 2011 International Joint Conference on Biometrics (IJCB), Oct. 2011, pp. 1–7.

S. Shirke, S.S.Pawar, and K. Shah, "Literature Review: Model Free Human Gait Recognition," in 2014 Fourth International Conference on Communication Systems and Network Technologies, Apr. 2014, pp. 891–895.

X. Wang and S. Feng, "Multi‐perspective gait recognition based on classifier fusion," IET Image Processing, vol. 13, no. 11, pp. 1885–1891, Sept. 2019.

Md. Z. Uddin et al., "The OU-ISIR Large Population Gait Database with real-life carried object and its performance evaluation," IPSJ Transactions on Computer Vision and Applications, vol. 10, no. 1, Dec. 2018, Art. no. 5.

A. Nandy, R. Chakraborty, and P. Chakraborty, "Cloth invariant gait recognition using pooled segmented statistical features," Neurocomputing, vol. 191, pp. 117–140, May 2016.

T. Huang, X. Ben, C. Gong, W. Xu, Q. Wu, and H. Zhou, "GaitDAN: Cross-View Gait Recognition via Adversarial Domain Adaptation," IEEE Transactions on Circuits and Systems for Video Technology, vol. 34, no. 9, pp. 8026–8040, Sept. 2024.

Md. Z. Uddin, K. Hasan, M. A. R. Ahad, and F. Alnajjar, "Horizontal and Vertical Part-wise Feature Extraction for Coss-view Gait Recognition," IEEE Access, pp. 1–1, 2024.

K. Shiraga, Y. Makihara, D. Muramatsu, T. Echigo, and Y. Yagi, "GEINet: View-invariant gait recognition using a convolutional neural network," in 2016 International Conference on Biometrics (ICB), June 2016, pp. 1–8.

Y. L. Ng, X. Jiang, Y. Zhang, S. B. Shin, and R. Ning, "Automated Activity Recognition with Gait Positions Using Machine Learning Algorithms," Engineering, Technology & Applied Science Research, vol. 9, no. 4, pp. 4554–4560, Aug. 2019.

D. Thapar, A. Nigam, D. Aggarwal, and P. Agarwal, "VGR-net: A view invariant gait recognition network," in 2018 IEEE 4th International Conference on Identity, Security, and Behavior Analysis (ISBA), Jan. 2018, pp. 1–8.

N. Takemura, Y. Makihara, D. Muramatsu, T. Echigo, and Y. Yagi, "On Input/Output Architectures for Convolutional Neural Network-Based Cross-View Gait Recognition," IEEE Transactions on Circuits and Systems for Video Technology, vol. 29, no. 9, pp. 2708–2719, Sept. 2019.

F. M. Castro, M. J. Marín-Jiménez, N. Guil, and N. Pérez De La Blanca, "Multimodal feature fusion for CNN-based gait recognition: an empirical comparison," Neural Computing and Applications, vol. 32, no. 17, pp. 14173–14193, Sept. 2020.

T. Liu, X. Ye, and B. Sun, "Combining Convolutional Neural Network and Support Vector Machine for Gait-based Gender Recognition," in 2018 Chinese Automation Congress (CAC), Nov. 2018, pp. 3477–3481.

S. Muhammed and E. Çelebi, "CAMNet: DeepGait Feature Extraction via Maximum Activated Channel Localization," Intelligent Automation & Soft Computing, vol. 28, no. 2, pp. 397–416, 2021.

C. Fan et al., "GaitPart: Temporal Part-Based Model for Gait Recognition," in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020, pp. 14213–14221.

S. Gul, M. I. Malik, G. M. Khan, and F. Shafait, "Multi-view gait recognition system using spatio-temporal features and deep learning," Expert Systems with Applications, vol. 179, Oct. 2021, Art. no. 115057.

C. Zhang, W. Liu, H. Ma, and H. Fu, "Siamese neural network based gait recognition for human identification," in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Mar. 2016, pp. 2832–2836.

M. A. Khan et al., "Human gait analysis for osteoarthritis prediction: a framework of deep learning and kernel extreme learning machine," Complex & Intelligent Systems, vol. 9, no. 3, pp. 2665–2683, June 2023.

T. Wolf, M. Babaee, and G. Rigoll, "Multi-view gait recognition using 3D convolutional neural networks," in 2016 IEEE International Conference on Image Processing (ICIP), Sept. 2016, pp. 4165–4169.

T. Yeoh, H. E. Aguirre, and K. Tanaka, "Clothing-invariant gait recognition using convolutional neural network," in 2016 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), Oct. 2016, pp. 1–5.

A. Sokolova and A. Konushin, "Pose‐based deep gait recognition," IET Biometrics, vol. 8, no. 2, pp. 134–143, Mar. 2019.

D. Thapar, G. Jaswal, A. Nigam, and C. Arora, "Gait metric learning siamese network exploiting dual of spatio-temporal 3D-CNN intra and LSTM based inter gait-cycle-segment features," Pattern Recognition Letters, vol. 125, pp. 646–653, July 2019.

M. Babaee, L. Li, and G. Rigoll, "Person identification from partial gait cycle using fully convolutional neural networks," Neurocomputing, vol. 338, pp. 116–125, Apr. 2019.

A. Dey, S. Biswas, and L. Abualigah, "Efficient Violence Recognition in Video Streams using ResDLCNN-GRU Attention Network," ECTI Transactions on Computer and Information Technology (ECTI-CIT), vol. 18, no. 3, pp. 329–341, July 2024.

B. K. P. Horn and B. G. Schunck, "Determining optical flow," Artificial Intelligence, vol. 17, no. 1–3, pp. 185–203, Aug. 1981.

Y. Fu, Shibei Meng, Saihui Hou, Xuecai Hu, and Yongzhen Huang, "CASIA-B Pose." Science Data Bank, Aug. 17, 2023.

Y. Fu, S. Meng, S. Hou, X. Hu, and Y. Huang, "GPGait: Generalized Pose-based Gait Recognition," in 2023 IEEE/CVF International Conference on Computer Vision (ICCV), Oct. 2023, pp. 19538–19547.

H. Chao, Y. He, J. Zhang, and J. Feng, "GaitSet: Regarding Gait as a Set for Cross-View Gait Recognition," Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, no. 01, pp. 8126–8133, July 2019.

K. Apostolidis, P. Amanatidis, and G. Papakostas, "Performance Evaluation of Convolutional Neural Networks for Gait Recognition," in 24th Pan-Hellenic Conference on Informatics, Nov. 2020, pp. 61–63.