Increasing validation accuracy of a face mask detection by new deep learning model-based classification

Joodi, Mohanad Azeez; Saleh, Muna Hadi; Kadhim, Dheyaa Jasim

doi:10.11591/ijeecs.v29.i1.pp304-314

Cited by 5 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generally, there has been a lot of focus on computation cost [ 30 , 31 ]. It is considered as a key element which assist in ill-conditioning.…”

Section: Introductionmentioning

confidence: 99%

Performance enhancement of high order Hahn polynomials using multithreading

Mahmmod,

Flayyih,

Fakhri

et al. 2023

PLoS ONE

View full text Add to dashboard Cite

Orthogonal polynomials and their moments have significant role in image processing and computer vision field. One of the polynomials is discrete Hahn polynomials (DHaPs), which are used for compression, and feature extraction. However, when the moment order becomes high, they suffer from numerical instability. This paper proposes a fast approach for computing the high orders DHaPs. This work takes advantage of the multithread for the calculation of Hahn polynomials coefficients. To take advantage of the available processing capabilities, independent calculations are divided among threads. The research provides a distribution method to achieve a more balanced processing burden among the threads. The proposed methods are tested for various values of DHaPs parameters, sizes, and different values of threads. In comparison to the unthreaded situation, the results demonstrate an improvement in the processing time which increases as the polynomial size increases, reaching its maximum of 5.8 in the case of polynomial size and order of 8000 × 8000 (matrix size). Furthermore, the trend of continuously raising the number of threads to enhance performance is inconsistent and becomes invalid at some point when the performance improvement falls below the maximum. The number of threads that achieve the highest improvement differs according to the size, being in the range of 8 to 16 threads in 1000 × 1000 matrix size, whereas at 8000 × 8000 case it ranges from 32 to 160 threads.

show abstract

“…Generally, there has been a lot of focus on computation cost [ 30 , 31 ]. It is considered as a key element which assist in ill-conditioning.…”

Section: Introductionmentioning

confidence: 99%

Performance enhancement of high order Hahn polynomials using multithreading

Mahmmod,

Flayyih,

Fakhri

et al. 2023

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…The suggested deep model uses less computing time without compromising accuracy. A volume of input is divided into several volumes in the model, and a tree is generated for each volume (Masud et al, 2020;Joodi, 2023). Facial recognition and cloud-based mobile edge computing are suggested to provide an immersive online biometric authentication method for online guiding.…”

Section: Introductionmentioning

confidence: 99%

Proposed Face Detection Classification Model Based on Amazon Web Services Cloud (AWS)

Joodi

Saleh

Khadhim³

2023

jcoeng

View full text Add to dashboard Cite

One of the most important features of the Amazon Web Services (AWS) cloud is that the program can be run and accessed from any location. You can access and monitor the result of the program from any location, saving many images and allowing for faster computation. This work proposes a face detection classification model based on AWS cloud aiming to classify the faces into two classes: a non-permission class, and a permission class, by training the real data set collected from our cameras. The proposed Convolutional Neural Network (CNN) cloud-based system was used to share computational resources for Artificial Neural Networks (ANN) to reduce redundant computation. The test system uses Internet of Things (IoT) services through our cameras system to capture the images and upload them to the Amazon Simple Storage Service (AWS S3) cloud. Then two detectors were running, Haar cascade and multitask cascaded convolutional neural networks (MTCNN), at the Amazon Elastic Compute (AWS EC2) cloud, after that the output results of these two detectors are compared using accuracy and execution time. Then the classified non-permission images are uploaded to the AWS S3 cloud. The validation accuracy of the offline augmentation face detection classification model reached 98.81%, and the loss and mean square error were decreased to 0.0176 and 0.0064, respectively. The execution time of all AWS cloud systems for one image when using Haar cascade and MTCNN detectors reached three and seven seconds, respectively.

show abstract

“…Several neural network classifers are applied to the Twitter-collected dataset of people's faces. Human accuracy is just 26.96%, whereas the best accuracy attained is 53.2% [7,8]. A linear SVM classifer and a multilabel, deep learning-based facial action detector beat cutting-edge methods (HOG and LBP), are used.…”

Section: Introductionmentioning

confidence: 99%

A New Proposed Hybrid Learning Approach with Features for Extraction of Image Classification

Joodi

Saleh

Kadhim

2023

Journal of Robotics

Self Cite

View full text Add to dashboard Cite

Image classification is the process of finding common features in images from various classes and applying them to categorize and label them. The main problem of the image classification process is the abundance of images, the high complexity of the data, and the shortage of labeled data, presenting the key obstacles in image classification. The cornerstone of image classification is evaluating the convolutional features retrieved from deep learning models and training them with machine learning classifiers. This study proposes a new approach of “hybrid learning” by combining deep learning with machine learning for image classification based on convolutional feature extraction using the VGG-16 deep learning model and seven classifiers. A hybrid supervised learning system that takes advantage of rich intermediate features extracted from deep learning compared to traditional feature extraction to boost classification accuracy and parameters is suggested. They provide the same set of characteristics to discover and verify which classifier yields the best classification with our new proposed approach of “hybrid learning.” To achieve this, the performance of classifiers was assessed depending on a genuine dataset that was taken by our camera system. The simulation results show that the support vector machine (SVM) has a mean square error of 0.011, a total accuracy ratio of 98.80%, and an F1 score of 0.99. Moreover, the results show that the LR classifier has a mean square error of 0.035 and a total ratio of 96.42%, and an F1 score of 0.96 comes in the second place. The ANN classifier has a mean square error of 0.047 and a total ratio of 95.23%, and an F1 score of 0.94 comes in the third place. Furthermore, RF, WKNN, DT, and NB with a mean square error and an F1 score advance to the next stage with accuracy ratios of 91.66%, 90.47%, 79.76%, and 75%, respectively. As a result, the main contribution is the enhancement of the classification performance parameters with images of varying brightness and clarity using the proposed hybrid learning approach.

show abstract

Increasing validation accuracy of a face mask detection by new deep learning model-based classification

Cited by 5 publications

References 20 publications

Performance enhancement of high order Hahn polynomials using multithreading

Performance enhancement of high order Hahn polynomials using multithreading

Proposed Face Detection Classification Model Based on Amazon Web Services Cloud (AWS)

A New Proposed Hybrid Learning Approach with Features for Extraction of Image Classification

Contact Info

Product

Resources

About