Gait Silhouette Enhancement with Modified CLAHE and Precise Gait Recognition Using a Lightweight Convolutional Neural Network
Keywords:
Deep Learning, Gait recognition, Human Gait cycle detection, Silhouette enhancement techniqueAbstract
Gait recognition is a behavioural biometric that can recognize an individual from a distance based on their walking pattern. Gait recognition techniques are persistently evolving for security purposes, as new advances in person recognition, range from traditional machine learning to deep learning. Various circumstances, such as lighting conditions, wearing garments, carrying a bag, and walking surfaces, can affect gait recognition performance. Furthermore, gait recognition from different points of view is a big challenge. A new framework, GRLNet: Light-weight Convolution Neural Network for Gait Recognition is proposed to identify the individual in various lighting conditions, clothing, etc. GRLNet is a portable architecture with a reduced memory size. Depth-wise and point-wise separable convolution is used to reduce the floating–point operations (FLOPs) and several parameters. A novel Hamming Correlated Gait Cycle Detection and Modified Contrast Limited Adaptive Histogram Equalization (MCLAHE) for gait silhouette image is proposed to enhance the gait energy image. Experiments on the popular public benchmark CASIA-B dataset was done to evaluate the efficiency of our proposed framework and our approach outperformed state-of-the-art solutions with covariates of carrying bag and wearing different clothes.
Downloads
References
Matovski, D.S., Nixon, M.S., Carter, J.N. (2014). Gait Recognition. In K. Ikeuchi (Ed.), Computer Vision. Springer.
Di Gregorio, R., & Vocenas, L. (2021). Identification of Gait-Cycle Phases for Prosthesis Control. Biomimetics (Basel), 6(2), 22.
Khan, M. A., Fathima, S. S., Stepnila, B. A., Ali, A. M. I., Mohamed Ifthikar Ali, A. (2020). Joint intensity transformer network for gait recognition robust against clothing and carrying status. Materials Today: Proceedings, 33(7), 3008-3020.
Sepas-Moghaddam, A., & Etemad, A. (2022). Deep Gait Recognition: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence.
Zheng, Z., Zheng, L., & Yang, Y. (2017). Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. arXiv:1701.07717v1.
Zheng, L., Huang, Y., Lu, H., & Yang, Y. (2017). Pose invariant embedding for deep person re-identification. arXiv:1701.07732v1.
Yao, L., Kusakunniran, W., Wu, Q., Zhang, J., & Tang, Z. (2018). Robust CNN-based Gait Verification and Identification using Skeleton Gait Energy Image. 2018 Digital Image Computing: Techniques and Applications (DICTA).
Hawas, A. R., El-Khobby, H. A., Abd-Elnaby, M., & Abd El-Samie, F. E. (2019). Gait identification by convolutional neural networks and optical flow. Multimedia Tools and Applications.
Xu, Z., Lu, W., Zhang, Q., Yeung, Y., & Chen, X. (2019). Gait recognition based on capsule network. Journal of Visual Communication and Image Representation, 59, 159-167.
Shao, X., Nie, X., Zhao, X., Zheng, R., & Guo, D. (2020). Gait Recognition based on Improved LeNet Network. 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC).
Wang, X., & Zhang, J. (2020). Gait feature extraction and gait classification using two-branch CNN. Multimedia Tools and Applications, 79, 2917–2930.
Arshad, H., Sharif, M. I., Yasmin, M., Tavares, J. M. R., & Zhang, Y. D. (2020). A multilevel paradigm for deep convolutional neural network features selection with an application to human gait recognition. Expert Systems.
Mehmood, A., Khan, M. A., Khan, S. A., Shaheen, M., & Saba, T. (2020). Prosperous human gait recognition: An end-to-end system based on pre-trained CNN features selection. Multimedia Tools and Applications, 2, 1–21.
Khan, A., Attique Khan, M., Younus Javed, M., Alhaisoni, M., & Tariq, U. (2022). Human gait recognition using deep learning and improved ant colony optimization. Computers, Materials & Continua, 70(2), 2113–2130.
Ghosh, R. (2022). A Faster R-CNN and recurrent neural network-based approach of gait recognition with and without carried objects. Expert Systems with Applications, 205, 117730..
Liu, X., Chen, M., Liang, T., Lou, C., Wang, H., & Liu, X. (2022). A lightweight double-channel depthwise separable convolutional neural network for multimodal fusion gait recognition. Mathematical Biosciences and Engineering, 19(2), 1195-1212.
Luo, J., & Tjahjadi, T. (2020). View and Clothing Invariant Gait Recognition via 3D Human Semantic Folding. IEEE Access, 8, 100365-100383.
Asif, M., Tiwana, M. I., Khan, U. S., Ahmad, M. W., Qureshi, W. S., & Iqbal, J. (2022). Human gait recognition subject to different covariate factors in a multi-view environment. Results in Engineering, 15, 100556.
CASIA-B dataset, Center for Biometrics and Security Research. Accessed: Dec. 11, 2021. [Online]. Available: http://www.cbsr.ia.ac.cn/users/szheng/.
Moré, L., Brizuela, M., Legal-Ayala, H., Pinto-Roa, D., Luis, J., & Vazquez Noguera, J. (2015). Parameter tuning of CLAHE based on multi-objective optimization to achieve different contrast levels in medical images. 2015 IEEE International Conference on Image Processing (ICIP). 10.1109/ICIP.2015.7351687.
Sugandhi, K., Wahid, F. F., & Raju, G. (2017). Detection of human gait cycle: An overlap based approach. 2017 International Conference on Infocom Technologies and Unmanned Systems (Trends and Future Directions) (ICTUS).
Samanta, P., & Jain, S. (2021). Analysis of Perceptual Hashing Algorithms in Image Manipulation Detection. Procedia Computer Science, 185, 203-212.
Witten, I. H., Frank, E., Hall, M. A., & Pal, C. J. (2017). Deep learning. In Data Mining (Fourth Edition). Morgan Kaufmann.
Watanabe, S., & Yamana, H. (2022). Overfitting measurement of convolutional neural networks using trained network weights. International Journal of Data Science and Analytics, 14, 261–278.
Xie, T., Liu, M., Deng, J., Cheng, X., Wang, X., & Liu, M. (2022). FocusedDropout for Convolutional Neural Network. arXiv, abs/2103.15425.
Jia, W., Sun, M., Lian, J., et al. (2022). Feature dimensionality reduction: a review. Complex Intelligent Systems, 8, 2663–2693.
Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. arXiv Prepr., 1610–2357.
Liang, F., Tian, Z., Dong, M., Cheng, S., Sun, L., Li, H., & Chen, Y. (2021). Efficient neural network using pointwise convolution kernels with linear phase constraint. Neurocomputing, 423, 572-579.
Alotaibi, M., & Mahmood, A. (2017). Improved gait recognition based on specialized deep convolutional neural network. Computer Vision and Image Understanding, 164, 103-110.
Mehmood, A., Khan, M. A., Khan, S. A., Shaheen, M., & Saba, T. (2022). Human Gait Recognition: A Deep Learning and Best Feature Selection Framework. Computers, Materials and Continua, 70, 343-360..
Wang, X., & Zhang, J. (2020). Gait feature extraction and gait classification using two-branch CNN. Multimedia Tools Appl, 79, 2917–2930.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
