The Human Gait Recognition using an Enhanced Convolutional Neural Network

Gait is a soft biometric with unique advantages compared to other biometrics. Soft biometric are features that can be extracted remotely and do not require human interaction. The force of gait, is that it does not require cooperative subjects and it is recognizable from low-resolution surveillance...

Full description

Saved in:
Bibliographic Details
Main Authors: Fatima Esmail, Ziyad Tariq Mustafa Al-Ta'i
Format: Article
Language:English
Published: College of science, university of Diyala 2024-07-01
Series:Academic Science Journal
Subjects:
Online Access:https://acadscij.uodiyala.edu.iq/index.php/Home/article/view/180
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849221182126030848
author Fatima Esmail
Ziyad Tariq Mustafa Al-Ta'i
author_facet Fatima Esmail
Ziyad Tariq Mustafa Al-Ta'i
author_sort Fatima Esmail
collection DOAJ
description Gait is a soft biometric with unique advantages compared to other biometrics. Soft biometric are features that can be extracted remotely and do not require human interaction. The force of gait, is that it does not require cooperative subjects and it is recognizable from low-resolution surveillance videos. This paper presents a proposed framework for gait recognition by building the required dataset. In this work, nine gait attributes are extracted, and recognition is done using an Enhanced Convolutional Neural Network (ECNN). The proposed model achieved an accuracy of 89.583%.
format Article
id doaj-art-3bc13d0997444b07bfb904712200c5d9
institution Kabale University
issn 2958-4612
2959-5568
language English
publishDate 2024-07-01
publisher College of science, university of Diyala
record_format Article
series Academic Science Journal
spelling doaj-art-3bc13d0997444b07bfb904712200c5d92024-11-19T10:00:14ZengCollege of science, university of DiyalaAcademic Science Journal2958-46122959-55682024-07-012310.24237/ASJ.02.03.796BThe Human Gait Recognition using an Enhanced Convolutional Neural NetworkFatima Esmail0Ziyad Tariq Mustafa Al-Ta'iAL-Timeme Gait is a soft biometric with unique advantages compared to other biometrics. Soft biometric are features that can be extracted remotely and do not require human interaction. The force of gait, is that it does not require cooperative subjects and it is recognizable from low-resolution surveillance videos. This paper presents a proposed framework for gait recognition by building the required dataset. In this work, nine gait attributes are extracted, and recognition is done using an Enhanced Convolutional Neural Network (ECNN). The proposed model achieved an accuracy of 89.583%. https://acadscij.uodiyala.edu.iq/index.php/Home/article/view/180Gait recognitionSoft BiometricsMediaPipeEnhanced Convolutional Neural Networks
spellingShingle Fatima Esmail
Ziyad Tariq Mustafa Al-Ta'i
The Human Gait Recognition using an Enhanced Convolutional Neural Network
Academic Science Journal
Gait recognition
Soft Biometrics
MediaPipe
Enhanced Convolutional Neural Networks
title The Human Gait Recognition using an Enhanced Convolutional Neural Network
title_full The Human Gait Recognition using an Enhanced Convolutional Neural Network
title_fullStr The Human Gait Recognition using an Enhanced Convolutional Neural Network
title_full_unstemmed The Human Gait Recognition using an Enhanced Convolutional Neural Network
title_short The Human Gait Recognition using an Enhanced Convolutional Neural Network
title_sort human gait recognition using an enhanced convolutional neural network
topic Gait recognition
Soft Biometrics
MediaPipe
Enhanced Convolutional Neural Networks
url https://acadscij.uodiyala.edu.iq/index.php/Home/article/view/180
work_keys_str_mv AT fatimaesmail thehumangaitrecognitionusinganenhancedconvolutionalneuralnetwork
AT ziyadtariqmustafaaltai thehumangaitrecognitionusinganenhancedconvolutionalneuralnetwork
AT fatimaesmail humangaitrecognitionusinganenhancedconvolutionalneuralnetwork
AT ziyadtariqmustafaaltai humangaitrecognitionusinganenhancedconvolutionalneuralnetwork