Automatic face detection based on bidirectional recurrent neural network optimized by improved Ebola optimization search algorithm

Abstract Face detection is a multidisciplinary research subject that employs fundamental computer algorithms, image processing, and patterning. Neural networks, on the other hand, have been widely developed to solve challenges in the domains of feature extraction, pattern detection, and the like in...

Full description

Saved in:
Bibliographic Details
Main Authors: Guang Gao, Chuangchuang Chen, Kun Xu, Kai Liu, Arsam Mashhadi
Format: Article
Language:English
Published: Nature Portfolio 2024-11-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-79067-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846165413045469184
author Guang Gao
Chuangchuang Chen
Kun Xu
Kai Liu
Arsam Mashhadi
author_facet Guang Gao
Chuangchuang Chen
Kun Xu
Kai Liu
Arsam Mashhadi
author_sort Guang Gao
collection DOAJ
description Abstract Face detection is a multidisciplinary research subject that employs fundamental computer algorithms, image processing, and patterning. Neural networks, on the other hand, have been widely developed to solve challenges in the domains of feature extraction, pattern detection, and the like in general. The presented study investigates the DNN (deep neural networks) use in the creation of facial detection operating systems. In this study, a novel optimized deep network has been presented to face detection. In this paper, after using some preprocessing stages for contrast enhancement and increasing the data number for the next deep tool, they fed to a bidirectional recurrent neural network (BRNN). The network is optimized via a novel enhanced version of Ebola optimization algorithm to provide far greater accuracy. The suggested procedure is examined on GTFD (Georgia Tech Face Database) and the results indicate that the proposed technique significantly outperforms other comparative methods, attaining an accuracy of 94.3%, a precision of 93.51%, a recall of 94.53%, and an F1-score of 92.47%. Furthermore, the method exhibits resilience against various challenges, achieving an accuracy of 95.6% under occlusions, 96.3% under lighting variations, 94.8% under pose variations, and 92.4% under low resolution conditions. Simulation results depict that the suggested technique gives far greater accuracy in comparison with the other comparative approaches.
format Article
id doaj-art-8c3836464ba846fabfd664a31334635f
institution Kabale University
issn 2045-2322
language English
publishDate 2024-11-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-8c3836464ba846fabfd664a31334635f2024-11-17T12:18:52ZengNature PortfolioScientific Reports2045-23222024-11-0114111910.1038/s41598-024-79067-xAutomatic face detection based on bidirectional recurrent neural network optimized by improved Ebola optimization search algorithmGuang Gao0Chuangchuang Chen1Kun Xu2Kai Liu3Arsam Mashhadi4School of Network Engineering, Zhoukou Normal UniversitySchool of Network Engineering, Zhoukou Normal UniversitySchool of Network Engineering, Zhoukou Normal UniversitySchool of Software, Chongqing Finance and Economics CollegeUniversity of TehranAbstract Face detection is a multidisciplinary research subject that employs fundamental computer algorithms, image processing, and patterning. Neural networks, on the other hand, have been widely developed to solve challenges in the domains of feature extraction, pattern detection, and the like in general. The presented study investigates the DNN (deep neural networks) use in the creation of facial detection operating systems. In this study, a novel optimized deep network has been presented to face detection. In this paper, after using some preprocessing stages for contrast enhancement and increasing the data number for the next deep tool, they fed to a bidirectional recurrent neural network (BRNN). The network is optimized via a novel enhanced version of Ebola optimization algorithm to provide far greater accuracy. The suggested procedure is examined on GTFD (Georgia Tech Face Database) and the results indicate that the proposed technique significantly outperforms other comparative methods, attaining an accuracy of 94.3%, a precision of 93.51%, a recall of 94.53%, and an F1-score of 92.47%. Furthermore, the method exhibits resilience against various challenges, achieving an accuracy of 95.6% under occlusions, 96.3% under lighting variations, 94.8% under pose variations, and 92.4% under low resolution conditions. Simulation results depict that the suggested technique gives far greater accuracy in comparison with the other comparative approaches.https://doi.org/10.1038/s41598-024-79067-xFace detectionDeep learningBidirectional recurrent neural networkImproved Ebola optimization search algorithm
spellingShingle Guang Gao
Chuangchuang Chen
Kun Xu
Kai Liu
Arsam Mashhadi
Automatic face detection based on bidirectional recurrent neural network optimized by improved Ebola optimization search algorithm
Scientific Reports
Face detection
Deep learning
Bidirectional recurrent neural network
Improved Ebola optimization search algorithm
title Automatic face detection based on bidirectional recurrent neural network optimized by improved Ebola optimization search algorithm
title_full Automatic face detection based on bidirectional recurrent neural network optimized by improved Ebola optimization search algorithm
title_fullStr Automatic face detection based on bidirectional recurrent neural network optimized by improved Ebola optimization search algorithm
title_full_unstemmed Automatic face detection based on bidirectional recurrent neural network optimized by improved Ebola optimization search algorithm
title_short Automatic face detection based on bidirectional recurrent neural network optimized by improved Ebola optimization search algorithm
title_sort automatic face detection based on bidirectional recurrent neural network optimized by improved ebola optimization search algorithm
topic Face detection
Deep learning
Bidirectional recurrent neural network
Improved Ebola optimization search algorithm
url https://doi.org/10.1038/s41598-024-79067-x
work_keys_str_mv AT guanggao automaticfacedetectionbasedonbidirectionalrecurrentneuralnetworkoptimizedbyimprovedebolaoptimizationsearchalgorithm
AT chuangchuangchen automaticfacedetectionbasedonbidirectionalrecurrentneuralnetworkoptimizedbyimprovedebolaoptimizationsearchalgorithm
AT kunxu automaticfacedetectionbasedonbidirectionalrecurrentneuralnetworkoptimizedbyimprovedebolaoptimizationsearchalgorithm
AT kailiu automaticfacedetectionbasedonbidirectionalrecurrentneuralnetworkoptimizedbyimprovedebolaoptimizationsearchalgorithm
AT arsammashhadi automaticfacedetectionbasedonbidirectionalrecurrentneuralnetworkoptimizedbyimprovedebolaoptimizationsearchalgorithm