scholarly journals Cloud Based Face Recognition using Machine Learning

2021 ◽  
pp. 1003-1006
Author(s):  
Pramod R ◽  
Rakshanda D. Bellary ◽  
Riya Bharti ◽  
Sushma S
Keyword(s):  
Machine Learning ◽  
Face Recognition ◽  
Raspberry Pi ◽  
Authentication Mechanism ◽  
Face Images ◽  
Memory Card ◽  
Main Motive ◽  
Entrance Door ◽  
Identity Card ◽  
The Face

The main motive of this paper is to implement a system where the employees and the visitors are granted access to enter the office by recognizing their face images. And henceforth, the access is granted only when the employee or the visitor enters the correct pin into the keypad which is concerned for authentication purpose.Without any usage of the tag keys or identity card an employee can easily unlock the entrance door once his face is recognized. A Raspberry pi, a camera, a memory card and a keypad is the hardware components that is required in this system. The face recognition and the authentication carried out by the keypad is controlled by the cloud based platforms and the local based Web Services. The authentication mechanism and the face recognition provides a safe and and increased level of security which gives a protection against spoofing attacks where there is no need of carrying any tag keys or access cards.

Face recognition in an intelligent door lock with ResNet model based on deep learning

2021 ◽  
pp. 1-11
Author(s):  
Suphawimon Phawinee ◽  
Jing-Fang Cai ◽  
Zhe-Yu Guo ◽  
Hao-Ze Zheng ◽  
Guan-Chen Chen
Keyword(s):  
Face Recognition ◽  
Detection System ◽  
Low Cost ◽  
Ease Of Use ◽  
Raspberry Pi ◽  
Training Methods ◽  
Graphics Recognition ◽  
Face Images ◽  
The Face ◽  
Door Lock

Internet of Things is considerably increasing the levels of convenience at homes. The smart door lock is an entry product for smart homes. This work used Raspberry Pi, because of its low cost, as the main control board to apply face recognition technology to a door lock. The installation of the control sensing module with the GPIO expansion function of Raspberry Pi also improved the antitheft mechanism of the door lock. For ease of use, a mobile application (hereafter, app) was developed for users to upload their face images for processing. The app sends the images to Firebase and then the program downloads the images and captures the face as a training set. The face detection system was designed on the basis of machine learning and equipped with a Haar built-in OpenCV graphics recognition program. The system used four training methods: convolutional neural network, VGG-16, VGG-19, and ResNet50. After the training process, the program could recognize the user’s face to open the door lock. A prototype was constructed that could control the door lock and the antitheft system and stream real-time images from the camera to the app.

scholarly journals Expression Invariant Features for Face Recognition

2019 ◽  
Vol 9 (2) ◽  
pp. 2012-2016
Keyword(s):  
Machine Learning ◽  
Face Recognition ◽  
Facial Expression ◽  
Facial Expressions ◽  
Personal Computer ◽  
The Other ◽  
Machine Learning Methods ◽  
Face Images ◽  
Invariant Features ◽  
The Face

Personal Computer sourced Face Recognition has been a sophisticated and well-found technique which is being rationally utilized for most of the authenticated cases. In reality, there is a number of situations where the expressions of the face will be different. We are here able to instinctively detect the five universal expressions: smile, sadness, anger, surprise, neutral by studying face geometry by determining which type of facial expression has been carried out. Using some facial data with variant expressions. We hereby made some experimentations to calculate the accuracies of some machine learning methods by making some changes in the face images such as a change in expressions, which at last needed for training and recognition identifiers. Our objective is to take the features of neutral facial expressions and add them with the other expressive face images like smiling, angry, sadness to improve the accuracy.

scholarly journals Smart Door Lock/Unlock Using Raspberry Pi

2020 ◽  
pp. 543-548
Author(s):  
Sandesh R ◽  
Avinash Sridhar ◽  
Rishikesh T P ◽  
Saniya Farheen ◽  
Sara Tameem
Keyword(s):  
Face Recognition ◽  
Recognition System ◽  
Raspberry Pi ◽  
Face Images ◽  
Face Features ◽  
Image Capturing ◽  
The Face ◽  
Face Detection And Recognition ◽  
Door Lock ◽  
Human Faces

This paper deals with the proposed system for smart and savvy door lock recognition system which is essentially for identification of human faces and mainly for home security. This is divided into two sub systems. First is image capturing, then comes face detection and recognition and finally automatic door access management. Open CV is mainly used for Face Recognition because it uses Eigen faces which compares the face images and produces it without losing vital face features, facial images of various persons are going to be stored in database. The purpose of the paper is to take face recognition to height which can replace the use of standard passwords, pins and patterns, adding more security to our life. The process carried out by raspberry pi is fast and makes the system work smoother.

scholarly journals Voice Controlled Personal Assistive Bot with Object Detection

2021 ◽  
Vol 12 (4) ◽  
pp. 578-584
Author(s):  
S. A. Sivasankari, Et. al.
Keyword(s):  
Machine Learning ◽  
Face Recognition ◽  
Learning Algorithm ◽  
Raspberry Pi ◽  
Machine Learning Algorithm ◽  
Primary Reason ◽  
Person Detection ◽  
Personal Assistance ◽  
Human Voice ◽  
The Face

Currently innovation has made our lives simpler for individuals. Be that as it may, from this innovation, certain gatherings of individuals need more assistance and backing for old or handicap individuals. This innovation can make a method of having a typical life. Thus, we zeroed in on the idea of an individual colleague robot. The fundamental objectisto supply helptodebilitated people.ThisPerson alassistive Bot help to decrease the manual endeavors being put by people in their everyday errands. The intention is to execute a specialized work that is voice controlling one which can act as a PA that can performvarious errands or administrations for a person.This is uncommonly intended for this group of people asits primary reason for existing is to supply help to relate senior or debilitated individual. The human voice order is given to the mechanical right hand distantly,by utilizing a voice order.The automaton will perform different movements: Forward, Backward, Right, Left and start/stop activities. The robot can likewise peruse and perceive the letter sets and text and the words which are said by the person will check from the google dictionary and printasatext.The capability of the robotisto detect the objects and relocate the m from one place to another and includes the face recognition. So, our main ideology is to create a personal assistance bot, which is capable of handling small objects. We are planning to make the bot consisting of four wheels and an arm placed on top. Using Raspberry Pi, we are communicating the sensors and motors throughour voice commands. Smart assistants like Google for android,Sir ifor Apple,Corton a for Microsoft,the seassistive gives us a platform to communicate to a bot. Asweare programming on Python, Amodule name Pyaudio will helpto communicate with a bot and having the extra feature like ‘Speechto Text’.And we would like to add an extra feature like object and person detection. A Camera module will be installed for capturing video and recognize the Humans and objects carried out with Machine Learning Algorithm

Thermal Human Face Recognition for Biometric Security System

2013 ◽  
pp. 1-24 ◽  
Author(s):  
Ayan Seal ◽  
Debotosh Bhattacharjee ◽  
Mita Nasipuri ◽  
Dipak Kumar Basu
Keyword(s):  
Face Recognition ◽  
Thermal Infrared ◽  
Infrared Images ◽  
Human Machine Interaction ◽  
Human Face Recognition ◽  
Face Images ◽  
Thermal Infrared Images ◽  
The Face ◽  
Intensity Images ◽  
Machine Interaction

Automatic face recognition has been comprehensively studied for more than four decades, since face recognition of individuals has many applications, particularly in human-machine interaction and security. Although face recognition systems have achieved a significant level of maturity with some realistic achievement, face recognition still remains a challenging problem due to large variation in face images. Face recognition techniques can be generally divided into three categories based on the face image acquisition methodology: methods that work on intensity images, those that deal with video sequences, and those that require other sensory (like 3D sensory or infra-red imagery) data. Researchers are using thermal infrared images for face recognition. Since thermal infrared images have some advantages over 2D images. In this chapter, an overview of some of the well-known techniques of face recognition using thermal infrared faces are discussed, and some of the drawbacks and benefits of each of these methods mentioned therein are discussed. This chapter talks about some of the most recent algorithms developed for this purpose, and tries to give a brief idea of the state of the art of face recognition technology. The authors propose one approach for evaluating the performance of face recognition algorithms using thermal infrared images. They also note the results of several classifiers on a benchmark dataset (Terravic Facial Infrared Database).

3D Face Reconstruction from Two Orthogonal Images for Face Recognition Applications

2012 ◽  
pp. 223-239
Author(s):  
Stefano Berretti ◽  
Alberto Del Bimbo ◽  
Pietro Pala
Keyword(s):  
Face Recognition ◽  
Control Points ◽  
3D Face Reconstruction ◽  
3D Face ◽  
Face Reconstruction ◽  
Face Images ◽  
Model Control ◽  
3D Geometry ◽  
The Face ◽  
Manual Assistance

In this paper, an original hybrid 2D-3D face recognition approach is proposed using two orthogonal face images, frontal and side views of the face, to reconstruct the complete 3D geometry of the face. This is obtained using a model based solution, in which a 3D template face model is morphed according to the correspondence of a limited set of control points identified on the frontal and side images in addition to the model. Control points identification is driven by an Active Shape Model applied to the frontal image, whereas subsequent manual assistance is required for control points localization on the side view. The reconstructed 3D model is finally matched, using the iso-geodesic regions approach against a gallery of 3D face scans for the purpose of face recognition. Preliminary experimental results are provided on a small database showing the viability of the approach.

scholarly journals 3D Face Image Inpainting with Generative Adversarial Nets

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Tongxin Wei ◽  
Qingbao Li ◽  
Jinjin Liu ◽  
Ping Zhang ◽  
Zhifeng Chen
Keyword(s):  
Face Recognition ◽  
Recognition Performance ◽  
Image Inpainting ◽  
Face Image ◽  
Edge Information ◽  
3D Face ◽  
Face Images ◽  
The Face ◽  
Match Effect ◽  
Traditional Image

In the process of face recognition, face acquisition data is seriously distorted. Many face images collected are blurred or even missing. Faced with so many problems, the traditional image inpainting was based on structure, while the current popular image inpainting method is based on deep convolutional neural network and generative adversarial nets. In this paper, we propose a 3D face image inpainting method based on generative adversarial nets. We identify two parallels of the vector to locate the planer positions. Compared with the previous, the edge information of the missing image is detected, and the edge fuzzy inpainting can achieve better visual match effect. We make the face recognition performance dramatically boost.

scholarly journals Original and Mirror Face Images and Minimum Squared Error Classification for Visible Light Face Recognition

2015 ◽  
Vol 2015 ◽  
pp. 1-7
Author(s):  
Rong Wang
Keyword(s):  
Face Recognition ◽  
High Accuracy ◽  
Virtual Training ◽  
Face Images ◽  
Squared Error ◽  
Training Samples ◽  
Real World Applications ◽  
The Face ◽  
Error Classification ◽  
Accuracy Performance

In real-world applications, the image of faces varies with illumination, facial expression, and poses. It seems that more training samples are able to reveal possible images of the faces. Though minimum squared error classification (MSEC) is a widely used method, its applications on face recognition usually suffer from the problem of a limited number of training samples. In this paper, we improve MSEC by using the mirror faces as virtual training samples. We obtained the mirror faces generated from original training samples and put these two kinds of samples into a new set. The face recognition experiments show that our method does obtain high accuracy performance in classification.

scholarly journals Eigenvector Weighting Function in Face Recognition

2011 ◽  
Vol 2011 ◽  
pp. 1-15 ◽  
Author(s):  
Pang Ying Han ◽  
Andrew Teoh Beng Jin ◽  
Lim Heng Siong
Keyword(s):  
Face Recognition ◽  
Weighting Function ◽  
Subspace Learning ◽  
Linear Projection ◽  
Face Images ◽  
Locality Preserving ◽  
Learning Techniques ◽  
Dimensionality Reduction Technique ◽  
The Face ◽  
Face Subspace

Graph-based subspace learning is a class of dimensionality reduction technique in face recognition. The technique reveals the local manifold structure of face data that hidden in the image space via a linear projection. However, the real world face data may be too complex to measure due to both external imaging noises and the intra-class variations of the face images. Hence, features which are extracted by the graph-based technique could be noisy. An appropriate weight should be imposed to the data features for better data discrimination. In this paper, a piecewise weighting function, known as Eigenvector Weighting Function (EWF), is proposed and implemented in two graph based subspace learning techniques, namely Locality Preserving Projection and Neighbourhood Preserving Embedding. Specifically, the computed projection subspace of the learning approach is decomposed into three partitions: a subspace due to intra-class variations, an intrinsic face subspace, and a subspace which is attributed to imaging noises. Projected data features are weighted differently in these subspaces to emphasize the intrinsic face subspace while penalizing the other two subspaces. Experiments on FERET and FRGC databases are conducted to show the promising performance of the proposed technique.

The System of Face Recognition Design

2014 ◽  
Vol 644-650 ◽  
pp. 3943-3946
Author(s):  
Xiao Bin Yu ◽  
Zi Qiao Li ◽  
Wen Qiang Ke ◽  
Rui Peng Li ◽  
Kai Xiong
Keyword(s):  
Face Recognition ◽  
Skin Color ◽  
Color Space ◽  
Color Model ◽  
Face Images ◽  
Accurate Detection ◽  
Haar Features ◽  
The Face ◽  
The Media ◽  
Skin Color Model

The technology of face recognition is the media to face images as the identity of the face recognition system.Through the choice of color space and the establishment of skin color model, give a rough detection for the human's image, then use the face Haar features getting more accurate detection.

Sign in / Sign up

Export Citation Format

Share Document