VGG16-MLP: Gait Recognition with Fine-Tuned VGG-16 and Multilayer Perceptron
Source abstract
Abstract
Gait is a pattern of a person’s walking. The body movements of a person while walking makes the gait unique. Regardless of the uniqueness, the gait recognition process suffers under various factors, namely the viewing angle, carrying condition, and clothing. In this paper, a pre-trained VGG-16 model is incorporated with a multilayer perceptron to enhance the performance under various covariates. At first, the gait energy image is obtained by averaging the silhouettes over a gait cycle. Transfer learning and fine-tuning techniques are then applied on the pre-trained VGG-16 model to learn the gait features of the attained gait energy image. Subsequently, a multilayer perceptron is utilized to determine the relationship among the gait features and the corresponding subject. Lastly, the classification layer identifies the corresponding subject. Experiments are conducted to evaluate the performance of the proposed method on the CASIA-B dataset, the OU-ISIR dataset D, and the OU-ISIR large population dataset. The comparison with the state-of-the-art methods shows that the proposed method outperforms the methods on all the datasets.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Gait Recognition and Analysis · Hand Gesture Recognition Systems · Human Pose and Action Recognition
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Information Science and Technology, Multimedia University, Melaka 75450, Malaysia
Funding
the Ministry of Higher Education · Multimedia University Internal Research · Yayasan Universiti Multimedia
References (49)
Show source-provided references
1. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
2. Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21–26). Densely connected convolutional networks. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.243 ↗
3. Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012, January 3–6). Imagenet classification with deep convolutional neural networks. Proceedings of the Advances in Neural Information Processing Systems 25 (NIPS 2012), Lake Tahoe, NV, USA.
4. Vedaldi, A., and Zisserman, A. (2016). VGG Convolutional Neural Networks Practical, Department of Engineering Science, University of Oxford.
5. Zhen, H., Deng, M., Lin, P., and Wang, C. (2018, January 9–11). Human gait recognition based on deterministic learning and Kinect sensor. Proceedings of the 2018 Chinese Control And Decision Conference (CCDC), Shenyang, China.10.1109/CCDC.2018.8407426 ↗
6. Human gait recognition based on deterministic learning and data stream of Microsoft Kinect10.1109/TCSVT.2018.2883449 ↗
7. Skeleton-based gait recognition via robust frame-level matching10.1109/TIFS.2019.2901823 ↗
8. Sah, S., and Panday, S.P. (2020, January 17–19). Model Based Gait Recognition Using Weighted KNN. Proceedings of the 8th IOE Graduate Conference, London, UK.
9. Simple and efficient pose-based gait recognition method for challenging environments10.1007/s10044-020-00935-z ↗
10. Kehtarnavaz, N., and Carlsohn, M.F. (2014, January 16–17). Gait recognition based on Kinect sensor. Proceedings of the Real-Time Image and Video Processing 2014, Brussels, Belgium.
11. Sattrupai, T., and Kusakunniran, W. (2018, January 28–31). Deep trajectory based gait recognition for human re-identification. Proceedings of the TENCON 2018-2018 IEEE Region 10 Conference, Jeju, Korea.10.1109/TENCON.2018.8650523 ↗
12. View-invariant gait recognition based on kinect skeleton feature10.1007/s11042-018-5722-1 ↗
13. A machine learning method with threshold based parallel feature fusion and feature selection for automated gait recognition10.4018/JOEUC.2020040104 ↗
14. Gait probability image: An information-theoretic model of gait representation10.1016/j.jvcir.2014.05.006 ↗
15. Time-sliced averaged motion history image for gait recognition10.1016/j.jvcir.2014.01.012 ↗
16. Mogan, J.N., Lee, C.P., and Tan, A.W.C. (2017, January 17–19). Gait recognition using temporal gradient patterns. Proceedings of the 2017 5th International Conference on Information and Communication Technology (ICoIC7), Melaka, Malaysia.10.1109/ICoICT.2017.8074680 ↗
17. Mogan, J.N., Lee, C.P., Lim, K.M., and Tan, A.W.C. (2017, January 27–29). Gait recognition using binarized statistical image features and histograms of oriented gradients. Proceedings of the 2017 International Conference on Robotics, Automation and Sciences (ICORAS), Melaka, Malaysia.10.1109/ICORAS.2017.8308067 ↗
18. Rida, I. (2019). Towards human body-part learning for model-free gait recognition. arXiv.
19. Multi-level features fusion and selection for human gait recognition: An optimized framework of Bayesian model and binomial distribution10.1007/s13042-019-00947-0 ↗
20. Fast gait parameter estimation for frontal view gait video data based on the model selection and parameter optimization approach
21. Gait recognition via optimally interpolated deformable contours10.1016/j.patrec.2013.01.013 ↗
22. Review on vision-based gait recognition: Representations, classification schemes and datasets10.3844/ajassp.2017.252.266 ↗
23. Lishani, A., Boubchir, L., and Bouridane, A. (2014, January 14–17). Haralick features for GEI-based human gait recognition. Proceedings of the 2014 26th International Conference on Microelectronics (ICM), Doha, Qatar.10.1109/ICM.2014.7071800 ↗
24. Gait recognition with transient binary patterns10.1016/j.jvcir.2015.09.006 ↗
25. Alvarez, I.R.T., and Sahonero-Alvarez, G. (2018, January 20–22). Gait Recognition Based on Modified Gait Energy Image. Proceedings of the 2018 IEEE Sciences and Humanities International Research Conference (SHIRCON), Lima, Peru.
26. Spatiotemporal features of human motion for gait recognition10.1007/s11760-018-1365-y ↗
27. Mogan, J.N., Lee, C.P., and Lim, K.M. (2020). Gait recognition using histograms of temporal gradients. Journal of Physics: Conference Series, IOP Publishing.
28. Yeoh, T., Aguirre, H.E., and Tanaka, K. (2016, January 24–27). Clothing-invariant gait recognition using convolutional neural network. Proceedings of the 2016 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), Phuket, Thailand.10.1109/ISPACS.2016.7824728 ↗
29. Shiraga, K., Makihara, Y., Muramatsu, D., Echigo, T., and Yagi, Y. (2016, January 13–16). GEINet: View-invariant gait recognition using a convolutional neural network. Proceedings of the 2016 International Conference on Biometrics (ICB), Halmstad, Sweden.10.1109/ICB.2016.7550060 ↗
30. Improved gait recognition based on specialized deep convolutional neural network10.1016/j.cviu.2017.10.004 ↗
31. Min, P.P., Sayeed, S., and Ong, T.S. (2019, January 24–26). Gait recognition using deep convolutional features. Proceedings of the 2019 7th International Conference on Information and Communication Technology (ICoICT), Kuala Lumpur, Malaysia.10.1109/ICoICT.2019.8835194 ↗
32. Tong, S., Ling, H., Fu, Y., and Wang, D. (2017, January 23–27). Cross-view gait identification with embedded learning. Proceedings of the Thematic Workshops of ACM Multimedia 2017, Mountain View, CA, USA.10.1145/3126686.3126753 ↗
33. Multi-view gait recognition based on a spatial-temporal deep neural network10.1109/ACCESS.2018.2874073 ↗
34. Aung, H.M.L., and Pluempitiwiriyawej, C. (2020, January 6). Gait biometric-based human recognition system using deep convolutional neural network in surveillance system. Proceedings of the 2020 Asia Conference on Computers and Communications (ACCC), Singapore.10.1109/ACCC51160.2020.9347899 ↗
35. LFN: Based on the convolutional neural network of gait recognition method
36. Su, J., Zhao, Y., and Li, X. (2020, January 4–8). Deep metric learning based on center-ranked loss for gait recognition. Proceedings of the ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain.10.1109/ICASSP40776.2020.9054645 ↗
37. Deep Features Based Multiview Gait Recognition
38. A Unified Perspective of Classification-Based Loss and Distance-Based Loss for Cross-View Gait Recognition10.1016/j.patcog.2021.108519 ↗
39. GaitSet: Cross-view gait recognition through utilizing gait as a deep set
40. Gait recognition for person re-identification10.1007/s11227-020-03409-5 ↗
41. A multilevel paradigm for deep convolutional neural network features selection with an application to human gait recognition10.1111/exsy.12541 ↗
42. Mehmood, A., Khan, M.A., Sharif, M., Khan, S.A., Shaheen, M., Saba, T., Riaz, N., and Ashraf, I. (2020). Prosperous human gait recognition: An end-to-end system based on pre-trained CNN features selection. Multimed. Tools Appl., 1–21.10.1007/s11042-020-08928-0 ↗
43. Ambika, K., and Radhika, K. (2021, January 19–20). View Invariant Gait Authentication Using Transfer Learning. Proceedings of the International Conference on Innovative Computing & Communication (ICICC), Delhi, India.
44. Gait-DenseNet: A hybrid convolutional neural network for gait recognition
45. Individual recognition using gait energy image10.1109/TPAMI.2006.38 ↗
46. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
47. Yu, S., Tan, D., and Tan, T. (2006, January 20–24). A framework for evaluating the effect of view angle, clothing and carrying condition on gait recognition. Proceedings of the 18th International Conference on Pattern Recognition (ICPR’06), Hong Kong, China.
48. The OU-ISIR gait database comprising the treadmill dataset10.2197/ipsjtcva.4.53 ↗
49. The OU-ISIR gait database comprising the large population dataset and performance evaluation of gait recognition10.1109/TIFS.2012.2204253 ↗