Deep Learning and Kurtosis-Controlled, Entropy-Based Framework for Human Gait Recognition Using Video Sequences

被引:24
作者
Sharif, Muhammad Imran [1 ]
Khan, Muhammad Attique [1 ]
Alqahtani, Abdullah [2 ]
Nazir, Muhammad [1 ]
Alsubai, Shtwai [2 ]
Binbusayyis, Adel [2 ]
Damasevicius, Robertas [3 ]
机构
[1] HITEC Univ Taxila, Dept Comp Sci, Taxila 47080, Pakistan
[2] Prince Sattam Bin Abdulaziz Univ, Coll Comp Engn & Sci, Al Kharj 11942, Saudi Arabia
[3] Silesian Tech Univ, Fac Appl Math, PL-44100 Gliwice, Poland
关键词
gait recognition; deep learning; feature selection; classification; video understanding; FEATURE-SELECTION; FEATURES; CLASSIFICATION; FUSION;
D O I
10.3390/electronics11030334
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Gait is commonly defined as the movement pattern of the limbs over a hard substrate, and it serves as a source of identification information for various computer-vision and image-understanding techniques. A variety of parameters, such as human clothing, angle shift, walking style, occlusion, and so on, have a significant impact on gait-recognition systems, making the scene quite complex to handle. In this article, we propose a system that effectively handles problems associated with viewing angle shifts and walking styles in a real-time environment. The following steps are included in the proposed novel framework: (a) real-time video capture, (b) feature extraction using transfer learning on the ResNet101 deep model, and (c) feature selection using the proposed kurtosis-controlled entropy (KcE) approach, followed by a correlation-based feature fusion step. The most discriminant features are then classified using the most advanced machine learning classifiers. The simulation process is fed by the CASIA B dataset as well as a real-time captured dataset. On selected datasets, the accuracy is 95.26% and 96.60%, respectively. When compared to several known techniques, the results show that our proposed framework outperforms them all.
引用
收藏
页数:23
相关论文
共 48 条
  • [1] Past, Present, and Future of Face Recognition: A Review
    Adjabi, Insaf
    Ouahabi, Abdeldjalil
    Benzaoui, Amir
    Taleb-Ahmed, Abdelmalik
    [J]. ELECTRONICS, 2020, 9 (08) : 1 - 53
  • [2] Metaheuristic Algorithms on Feature Selection: A Survey of One Decade of Research (2009-2019)
    Agrawal, Prachi
    Abutarboush, Hattan F.
    Ganesh, Talari
    Mohamed, Ali Wagdy
    [J]. IEEE ACCESS, 2021, 9 : 26766 - 26791
  • [3] Review on COVID-19 diagnosis models based on machine learning and deep learning approaches
    Alyasseri, Zaid Abdi Alkareem
    Al-Betar, Mohammed Azmi
    Abu Doush, Iyad
    Awadallah, Mohammed A.
    Abasi, Ammar Kamal
    Makhadmeh, Sharif Naser
    Alomari, Osama Ahmad
    Abdulkareem, Karrar Hameed
    Adam, Afzan
    Damasevicius, Robertas
    Mohammed, Mazin Abed
    Abu Zitar, Raed
    [J]. EXPERT SYSTEMS, 2022, 39 (03)
  • [4] BACKPROPAGATION AND STOCHASTIC GRADIENT DESCENT METHOD
    AMARI, S
    [J]. NEUROCOMPUTING, 1993, 5 (4-5) : 185 - 196
  • [5] Human gait recognition based on histogram of oriented gradients and Haralick texture descriptor
    Anusha, R.
    Jaidhar, C. D.
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2020, 79 (11-12) : 8213 - 8234
  • [6] Clothing invariant human gait recognition using modified local optimal oriented pattern binary descriptor
    Anusha, R.
    Jaidhar, C. D.
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2020, 79 (3-4) : 2873 - 2896
  • [7] Arai K., 2012, Proceedings of the 2012 Ninth International Conference on Information Technology: New Generations (ITNG), P656, DOI 10.1109/ITNG.2012.164
  • [8] Gait based authentication using gait information image features
    Arora, Parul
    Hanmandlu, Madasu
    Srivastava, Smriti
    [J]. PATTERN RECOGNITION LETTERS, 2015, 68 : 336 - 342
  • [9] A multilevel paradigm for deep convolutional neural network features selection with an application to human gait recognition
    Arshad, Habiba
    Khan, Muhammad Attique
    Sharif, Muhammad Irfan
    Yasmin, Mussarat
    Tavares, Joao Manuel R. S.
    Zhang, Yu-Dong
    Satapathy, Suresh Chandra
    [J]. EXPERT SYSTEMS, 2022, 39 (07)
  • [10] Multi-level features fusion and selection for human gait recognition: an optimized framework of Bayesian model and binomial distribution
    Arshad, Habiba
    Khan, Muhammad Attique
    Sharif, Muhammad
    Yasmin, Mussarat
    Javed, Muhammad Younus
    [J]. INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2019, 10 (12) : 3601 - 3618