International Journal of Engineering
Trends and Technology

Research Article | Open Access | Download PDF
Volume 74 | Issue 5 | Year 2026 | Article Id. IJETT-V74I5P113 | DOI : https://doi.org/10.14445/22315381/IJETT-V74I5P113

Improving Gait-Based Human Identification Under Variability Using Deep and Machine Learning Ensembles

Babita Sonare, Deepika Saxena, Vijay Katkar

Received Revised Accepted Published
26 Aug 2025 12 Mar 2026 28 Mar 2026 30 May 2026

Citation :

Babita Sonare, Deepika Saxena, Vijay Katkar, "Improving Gait-Based Human Identification Under Variability Using Deep and Machine Learning Ensembles," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 5, pp. 195-204, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I5P113

Abstract

This paper investigates the convolutional neural network ensembles with machine learning classifiers for individual identification based on Gait. Gait recognition is a biometric modality wherein a person's unique Gait is used to identify. However, when a person wears a different pair of shoes, carries a load on their back, or walks differently, their gait changes, making it more difficult to identify them. In light of this difficulty, this work suggests an ensemble method to optimize the precision and resilience of gait-based human identification systems. It does this by combining the CNN and LSTM with the machine learning classifier independently by providing features like Gait Energy Image (GEI), Accumulative Frame Difference Energy Image (AFDEI), and their fusion. The proposed system’s performance is meticulously checked with the existing system on the “CASIA B” dataset and shows remarkable outcomes, as proved by statistical validation. The proposed methodology is experimented on a newly generated dataset, PCCOE-GAIT, which has given comparable results.

Keywords

Biometrics, Gait, ML Classifiers, CNN, LSTM.

References

[1] Jashila Nair Mogan, Chin Poo Lee, and Kian Ming Lim, “Advances in Vision-based Gait Recognition: From Handcrafted to Deep Learning,” Sensors, vol. 22, no. 15, pp. 1-24, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[2] Ning Suo, Xu Qian, and Jinhui Zhao, “Gait Recognition based on KPCA and KNN,” 2010 The 2nd Conference on Environmental Science and Information Application Technology, Wuhan, China, pp. 432-435, 2010.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Emdad Hossain, and Girija Chetty, “A Multi-Modal Gait based Human Identity Recognition System based on Surveillance Videos,” 2012 6th International Conference on Signal Processing and Communication Systems, Gold Coast, QLD, Australia, pp. 1-4, 2012.
[CrossRef] [Google Scholar] [Publisher Link]

[4] Soumia Benbakreti, Samir Benbakreti, and Mohammed Benyettou, “Recognizing Human Gait in Video Sequences,” 2012 International Conference on Multimedia Computing and Systems, Tangiers, Morocco, pp. 323-327, 2012.
[CrossRef] [Google Scholar] [Publisher Link]

[5] Daniel A. Reid, Mark S. Nixon, and Sarah V. Stevenage, “Soft Biometrics; Human Identification using Comparative Descriptions,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 36, no. 6, pp. 1216-1228, 2014.
[CrossRef] [Google Scholar] [Publisher Link]

[6] Jing Luo et al., “Gait Recognition using GEI and AFDEI,” International Journal of Optics, vol. 2025, no. 1, pp. 1-5, 2015.
[CrossRef] [Google Scholar] [Publisher Link]

[7] Anup Nandy, Rupak Chakraborty, and Pavan Chakraborty, “Cloth Invariant Gait Recognition using Pooled Segmented Statistical Features,” Neurocomputing, vol. 191, pp. 117-140, 2016.
[CrossRef] [Google Scholar] [Publisher Link]

[8] Kristijan Lenac et al., “Extending Appearance based Gait Recognition with Depth Data,” Applied Science, vol. 9, no. 24, pp. 1-18, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[9] Hajra Masood, and Humera Farooq, “An Appearance Invariant Gait Recognition Technique using Dynamic Gait Features,” International Journal of Optics, vol. 2021, no. 1, pp. 1-15, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[10] Muhammad Sharif et al., “A Machine Learning Method with Threshold based Parallel Feature Fusion and Feature Selection for Automated Gait Recognition,” Journal of Organizational and End User Computing (JOEUC), vol. 32, no. 2, pp. 67-92, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[11] Francisco Manuel Castro et al., “Automatic Learning of Gait Signatures for People Identification,” Advances in Computational Intelligence: 14th International Work-Conference on Artificial Neural Networks, IWANN 2017, Cadiz, Spain, pp. 257-270, 2017.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Anubha Parashar et al., “Data Preprocessing and Feature Selection Techniques in Gait Recognition: A Comparative Study of Machine Learning and Deep Learning Approaches,” Pattern Recognition Letters, vol. 172, pp. 65-73, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[13] Win Kong et al., “Human Gait State Classification using Artificial Neural Network,” 2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing (CIMSIVP), Orlando, FL, USA, pp. 1-5, 2014.
[CrossRef] [Google Scholar] [Publisher Link]

[14] Shiqi Yu et al., “Invariant Feature Extraction for Gait Recognition using only one Uniform Model,” Neurocomputing, vol. 239, pp. 81-93, 2017.
[CrossRef] [Google Scholar] [Publisher Link]

[15] Xiuhui Wang, and Jiajia Zhang, “Gait Feature Extraction and Gait Classification using Two-Branch CNN,” Multimedia Tools and Applications, vol. 79, no. 3-4, pp. 2917-2930, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[16] Francisco M. Castro et al., “Multimodal Feature Fusion for CNN-based Gait Recognition: An Empirical Comparison,” Neural Computing and Applications, vol. 32, no. 17, pp. 14173-14193, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[17] David Kreuzer, and Michael Munz, “Deep Convolutional and LSTM Networks on Multi-Channel time Series Data for Gait Phase Recognition,” Sensors, vol. 21, no. 3, pp. 1-15, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[18] Saba Gul et al., “Multi-View Gait Recognition System using Spatio-Temporal Features and Deep Learning,” Expert Systems with Applications, vol. 179, pp. 1-9, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[19] Md. Iman Junaid, and Samit Ari, “Gait Identification using Ensemble Deep Learning Technique,” 2022 IEEE Silchar Subsection Conference (SILCON), Silchar, India, pp. 1-5, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Pa Pa Min, Shohel Sayeed, and Thian Song Ong, “Gait Recognition using Deep Convolutional Features,” 2019 7th International Conference on Information and Communication Technology (ICoICT), Kuala Lumpur, Malaysia, pp. 1-5, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[21] Abhishek Sheth et al., “Gait Recognition using Convolutional Neural Network,” International Journal of Online and Biomedical Engineering, vol. 19, no. 1, pp. 107-118, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[22] Jashila Nair Mogan et al., “Gait-CNN-ViT: Multi-Model Gait Recognition with Convolutional Neural Networks and Vision Transformer,” Sensors, vol. 23, no. 8, pp. 1-15, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[23] Kun Liu et al., “A Novel Gait Phase Recognition Method based on DPF-LSTM-CNN using Wearable Inertial Sensors,” Sensors, vol. 23, no. 13, pp. 1-17, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[24] Büşranur Yaprak, and Eyüp Gedikli, “Enhancing Part-based Gait Recognition via Ensemble Learning and Feature Fusion,” Pattern Analysis and Applications, vol. 28, no. 2, pp. 1-19, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[25] Qizhen Chen et al., “Gait Recognition based on Temporal Gait Information Enhancing,” MultiMedia Modeling: 30th International Conference, MMM 2024, Amsterdam, The Netherlands, pp. 451-463, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[26] Entesar T. Burges, Zakariya A. Oraibi, and Ali Wali, “Gait Recognition using CGAN and EfficientNet Deep Neural Networks,” Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2025), vol. 3, pp. 339-346, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[27] Kamrul Hasan et al., “MMF-Gait: A Multi-Model Fusion-Enhanced Gait Recognition Framework Integrating Convolutional and Attention Networks,” Symmetry, vol. 17, no. 7, pp. 1-24, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[28] Shuai Zheng et al., “Robust View Transformation Model for Gait Recognition,” 2011 18th IEEE International Conference on Image Processing, Brussels, Belgium, pp. 2073-2076, 2011.
[CrossRef] [Google Scholar] [Publisher Link]

[29] Changsheng Wan, Li Wang, and Vir V. Phoha, “A Survey on Gait Recognition,” ACM Computing Surveys (CSUR), vol. 51, no. 5, pp. 1-35, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[30] Helly M. Desai, and Vaibhav Gandhi, “A Survey: Background Subtraction Techniques,” International Journal of Scientific and Engineering Research, vol. 5, no. 12, 2014.
[Google Scholar]

[31] Laith Alzubaidi et al., “Review of Deep Learning: Concepts, CNN Architectures, Challenges, Applications, Future Directions,” Journal of Big Data, vol. 8, no. 1, pp. 1-74, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[32] Benjamin Lindemann et al., “A Survey on Long Short-Term Memory Networks for Time Series Prediction,” Procedia CIRP, vol. 99, pp. 650-655, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[33] Peng Zhang, Qiang Wu, and Jingsong Xu, “VT-GAN: View Transformation GAN for Gait Recognition Across Views,” 2019 International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary, pp. 1-8, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[34] Xiaoyang Liu, and Jinqiang Liu, “Gait Recognition Method of Underground Coal Mine Personnel based on Densely Connected Convolution Network and Stacked Convolutional Autoencoder,” Entropy, vol. 22, no. 6, pp. 1-17, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[35] Xiuhui Wang, and Ke Yan, “Gait Classification through CNN-based Ensemble Learning,” Multimedia Tools and Applications, vol. 80, no. 1, pp. 1565-1581, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[36] Sang-Soo Yeo et al., “A Triplet-Branch Convolutional Neural Network for Part-based Gait Recognition,” Computer Systems Science and Engineering, vol. 47, no. 2, pp. 2027-2047, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[37] Yalian Wu et al., “Gait Recognition based on Feedback Weight Capsule Network,” 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), Chongqing, China, pp. 155-160, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[38] Wanjiang Xu, “Deep Large Margin Nearest Neighbor for Gait Recognition,” Journal of Intelligent Systems, vol. 30, no. 1, pp. 604-619, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[39] Longhui Wei et al., “Person Transfer GAN to Bridge Domain Gap for Person Re-identification,” 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, pp. 79-88, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[40] Weijian Deng et al., “Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification,” 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, pp. 994-1003, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[41] Xinnan Ding et al., “Sequential Convolutional Network for Behavioral Pattern Extraction in Gait Recognition,” Neurocomputing, vol. 463, pp. 411-421, 2021.
        [CrossRef] [Google Scholar] [Publisher Link]