A multilevel paradigm for deep convolutional neural network features selection with an application to human gait recognition

被引:90
作者
Arshad, Habiba [1 ]
Khan, Muhammad Attique [2 ]
Sharif, Muhammad Irfan [3 ]
Yasmin, Mussarat [1 ]
Tavares, Joao Manuel R. S. [4 ]
Zhang, Yu-Dong [5 ]
Satapathy, Suresh Chandra [6 ]
机构
[1] COMSATS Univ Islamabad, Dept Comp Sci, Islamabad, Pakistan
[2] HITEC Univ, Dept Comp Sci, Taxila, Pakistan
[3] Univ Elect Sci & Technol China, Sch Comp Sci & Engn, Chengdu, Peoples R China
[4] Univ Porto, Inst Ciencia & Inovacao Engn Mecan & Engn Ind, Dept Engn Mecan, Fac Engn, Porto, Portugal
[5] Univ Leicester, Dept Informat, Leicester, Leics, England
[6] Kalinga Inst Ind Technol, Sch Comp Engn, Bhubaneswar, Odisha, India
关键词
gait recognition; CNN features; features selection; parallel fusion; recognition; SKIN-LESION DETECTION; FUSION; SEGMENTATION; REPRESENTATION; ENTROPY; CLASSIFICATION; IMPLEMENTATION; FRAMEWORK; DISEASES; GENDER;
D O I
10.1111/exsy.12541
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Human gait recognition (HGR) shows high importance in the area of video surveillance due to remote access and security threats. HGR is a technique commonly used for the identification of human style in daily life. However, many typical situations like change of clothes condition and variation in view angles degrade the system performance. Lately, different machine learning (ML) techniques have been introduced for video surveillance which gives promising results among which deep learning (DL) shows best performance in complex scenarios. In this article, an integrated framework is proposed for HGR using deep neural network and fuzzy entropy controlled skewness (FEcS) approach. The proposed technique works in two phases: In the first phase, deep convolutional neural network (DCNN) features are extracted by pre-trained CNN models (VGG19 and AlexNet) and their information is mixed by parallel fusion approach. In the second phase, entropy and skewness vectors are calculated from fused feature vector (FV) to select best subsets of features by suggested FEcS approach. The best subsets of picked features are finally fed to multiple classifiers and finest one is chosen on the basis of accuracy value. The experiments were carried out on four well-known datasets, namely, AVAMVG gait, CASIA A, B and C. The achieved accuracy of each dataset was 99.8, 99.7, 93.3 and 92.2%, respectively. Therefore, the obtained overall recognition results lead to conclude that the proposed system is very promising.
引用
收藏
页数:21
相关论文
共 82 条
[1]   Skin lesion segmentation and recognition using multichannel saliency estimation and M-SVM on selected serially fused features [J].
Akram T. ;
Khan M.A. ;
Sharif M. ;
Yasmin M. .
Journal of Ambient Intelligence and Humanized Computing, 2024, 15 (01) :1083-1102
[2]   Improved gait recognition based on specialized deep convolutional neural network [J].
Alotaibi, Munif ;
Mahmood, Ausif .
COMPUTER VISION AND IMAGE UNDERSTANDING, 2017, 164 :103-110
[3]   A novel machine learning approach for scene text extraction [J].
Ansari, Ghulam Jillani ;
Shah, Jamal Hussain ;
Yasmin, Mussarat ;
Sharif, Muhammad ;
Fernandes, Steven Lawrence .
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2018, 87 :328-340
[4]   Gait based authentication using gait information image features [J].
Arora, Parul ;
Hanmandlu, Madasu ;
Srivastava, Smriti .
PATTERN RECOGNITION LETTERS, 2015, 68 :336-342
[5]  
Arshad H, 2019, INT J PARALLEL EMERG, V2019, P1
[6]  
Battistone F., 2018, PATTERN RECOGNITION
[7]   A general tensor representation framework for cross-view gait recognition [J].
Ben, Xianye ;
Zhang, Peng ;
Lai, Zhihui ;
Yan, Rui ;
Zhai, Xinliang ;
Meng, Weixiao .
PATTERN RECOGNITION, 2019, 90 :87-98
[8]   Fundus Image Segmentation and Feature Extraction for the Detection of Glaucoma: A New Approach [J].
Bokhari, Syedia Tahseen Fatima ;
Sharif, Muhammad ;
Yasmin, Mussarat ;
Fernandes, Steven L. .
CURRENT MEDICAL IMAGING REVIEWS, 2018, 14 (01) :77-87
[9]   Fisher Motion Descriptor for Multiview Gait Recognition [J].
Castro, F. M. ;
Marin-Jimenez, M. J. ;
Guil Mata, N. ;
Munoz-Salinas, R. .
INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2017, 31 (01)
[10]  
Castro F. M., 2014, 2014 22 INT C PATT R