An Effective Implementation of Face Recognition Using Deep Convolutional Network

Najm, Hayder; Ansaf, Hayder; Hassen, Oday A.

doi:10.35741/issn.0258-2724.54.5.29

Cited by 10 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cryptography also helps individuals to use public and private media like the Internet, to shop and not be the victims of criminals and sniffing by a password. This is done through the use of modern technological advances in computer science [21][22][23][24][25][26].…”

Section: Information Securitymentioning

confidence: 99%

A New WoT Cryptography Algorithm Based on GOST and Novel 5d Chaotic System

Najm¹,

Hoomod

Hassan³

2021

Int. J. Interact. Mob. Technol.

Self Cite

View full text Add to dashboard Cite

The concept Web of Things (WoT) goes well beyond the emphasis on the Internet as a means of sharing data, instead of introducing all resources and connections involving computers, data, and people to the Web. It, therefore, focuses on a range of problems and opportunities, thus paving the way for several exciting industries applications. In cryptography a range of main characteristics of chaotic systems such as non-linearity, initial condition sensitivity, and mixing properties are available. These characteristics provide an essential connection between cryptography and chaos. GOST block cipher is based on secret key secrecy. However, when the encryption process with the same key is used for plaintext, the same cipher text is created. Message replication can be easily detected by an adversary who is a bad link in every communication. In this paper, propose to use a 5d chaotic system combined with GOST block cipher to create a new secure Web of Things (WoT) cryptography system. The 5D chaotic system was used to generate chaotic random keys used in GOST algorithm to provide proper security with as high hardness randomly enhances the NIST fifteen statistical tests and modifies key schedule as security operations.

show abstract

Section: Information Securitymentioning

confidence: 99%

A New WoT Cryptography Algorithm Based on GOST and Novel 5d Chaotic System

Najm¹,

Hoomod

Hassan³

2021

Int. J. Interact. Mob. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Various methodologies of the facial recognition approach are used for the classification process. The Artificial Intelligence method utilizes tools such as the neural networks technique and automatically recognizes faces of learning techniques [12], [27], e.g. Multi-Layer perceptron (MLP) with the backpropagation approach.…”

Section: Image Classificationmentioning

confidence: 99%

Facial Recognition Based on DWT – HOG – PCA Features with MLP Classifier

Luaibi¹,

Mohammed²

2019

Journal of Southwest Jiaotong University

View full text Add to dashboard Cite

Facial Recognition System has been widely used in various applications. Nevertheless, their efficiency rate fell dramatically when they were applied under unrestrained environments like the position of face, expression or illumination change. Because of these factors, it is essential to measure and calculate the performance rate of the dissimilar feature extraction techniques robust to such transformations in order to further integrate to a Facial Recognition System. This paper studies and evaluates the Histogram of Oriented Gradients method as a feature extraction method in order to deal with the abovementioned transformations. The study consists of four main phases: face detection, preprocessing, features extraction, and classification. Preprocessing is used to enhance the images by using the techniques of digital image processing. Feature extraction is used to get features from facial images based on the concept of Histogram Oriented Gradient feature that is applied to the facial image after conversion by means of the Discrete Wavelet Transform and vector reduction with the help of the Principle Component Analysis technique. Artificial neural network with the Back Propagation algorithm is used in training and testing as a classifier of the facial images to help recognize the face. To measure the performance of the method under consideration, some experiments were implemented using two datasets: ORL containing 400 facial images of 40 individuals that achieved the accuracy rate about 99.1%, and FERET containing 912 facial images of 152 individuals, which helped achieve accuracy rate about 94.5% at the multilayer perceptron neural network classifier.

show abstract

“…These days, face recognition is commonly used as the human face's primary biometric feature. Face detection, identification and differentiation is assurance of several approaches to one of the main areas of study for focused areas like legal applications where offenders or publications can be identified using their live features, actions and characteristics [1] [2] [3]. Face detection is also used for security, like in face locks etc.…”

Section: Introductionmentioning

confidence: 99%

Facial Mask Detection Using Transfer Learning with Resent 18 and MobileNetV2

Akhtary¹,

Akhtary²,

Karimi³

2022

IJMRA

View full text Add to dashboard Cite

Identification of individuals using face masks has become a widespread concern as a result of the coronavirus pandemic. One critical method of preventing pandemic spread is for persons to constantly wear masks in public places. To achieve the maximum possible accuracy, new approaches for face mask detection are being developed that utilize convolutional neural networks. These novel techniques attempt to construct a binary face classifier capable of categorizing pixels in an image as either faces or non faces. In this study, we created a model using Resnet18 and MobileNetv2 in order to obtain trustworthy results for picture categorization. Additionally, we constructed our model for detecting live webcam feeds utilizing Transfer Learning on these deep convolutional neural networks, as well as ImageNet weights and OpenCV.

show abstract

An Effective Implementation of Face Recognition Using Deep Convolutional Network

Cited by 10 publications

References 20 publications

A New WoT Cryptography Algorithm Based on GOST and Novel 5d Chaotic System

A New WoT Cryptography Algorithm Based on GOST and Novel 5d Chaotic System

Facial Recognition Based on DWT – HOG – PCA Features with MLP Classifier

Facial Mask Detection Using Transfer Learning with Resent 18 and MobileNetV2

Contact Info

Product

Resources

About