Android Based Face
Mask Detection System
APU KUMAR GIRI
4TH SEMESTER
MASTER OF COMPUTER APPLICATION
NIIS
INSTITUTE
OF
BUSINESS
ADMINISTRATION
BHUBANESWAR
Abstract
In order to effectively prevent the spread of COVID-19 virus, almost everyone wears
a mask during coronavirus epidemic. This almost makes conventional facial
recognition technology ineffective in many cases, such as community access control,
face access control, facial attendance, facial security checks at train stations, etc.
Therefore, it is very urgent to improve the recognition performance of the existing
face recognition technology on the masked faces. Most current advanced face
recognition approaches are designed based on deep learning, which depend on a
large number of face samples. However, at present, there are no publicly available
masked face recognition datasets. To this end, this work proposes three types of
masked face datasets, including Masked Face Detection Dataset (MFDD), Real-world
Masked Face Recognition Dataset (RMFRD) and Simulated Masked Face Recognition
Dataset (SMFRD). Among them, to the best of our knowledge, RMFRD is currently the
world's largest real-world masked face dataset. These datasets are freely available
to industry and academia, based on which various applications on masked faces can
be developed
NIIS
INSTITUTE
OF
BUSINESS
ADMINISTRATION
BHUBANESWAR
Introduction
Face recognition is a promising area of applied computer vision [1]. This
technique is used to recognize a face or identify a person automatically from
given images. In our daily life activates like, in a passport checking, smart
door, access control, voter verification, criminal investigation, and many other
purposes face recognition is widely used to authenticate a person correctly and
automatically. Face recognition has gained much attention as a unique,
reliable biometric recognition technology that makes it most popular than any
other biometric technique likes password, pin, fingerprint, etc. Many of the
governments across the world also interested in the face recognition system to
secure public places such as parks, airports, bus stations, and railway stations,
etc. Face recognition is one of the well-studied reallife problems. Excellent
progress has been done against face recognition technology
NIIS
INSTITUTE
OF
BUSINESS
ADMINISTRATION
BHUBANESWAR
Existing System:
Support Vector Machine
Discrete Wavelet Transform
NIIS
INSTITUTE
OF
BUSINESS
ADMINISTRATION
BHUBANESWAR
Drawbacks
 Existing face recognition solutions are no longer reliable when wearing a
mask.
Time consuming Process
Poor Detection
NIIS
INSTITUTE
OF
BUSINESS
ADMINISTRATION
BHUBANESWAR
Block Diagram
Input
Pre-
processing
Cropping
Face image
CNN
classification
obile set
modelsCaff
e m
Database
Without
mask
With Mask
NIIS
INSTITUTE
OF
BUSINESS
ADMINISTRATION
BHUBANESWAR
Preprocessing
Preprocessing is the data preprocessing and data augmentation module of
the Keras deep learning library. It provides utilities for working with image data, text
data, and sequence data
NIIS
INSTITUTE
OF
BUSINESS
ADMINISTRATION
BHUBANESWAR
CNN Structure
NIIS
INSTITUTE
OF
BUSINESS
ADMINISTRATION
BHUBANESWAR
Cnn classification
CNN description
Input Layer: This layer holds the raw input of image with width 32, height 32 and
depth
Convolution Layer: This layer computes the output volume by computing dot product
between all filters and image patch. Suppose we use total 12 filters for this layer we’ll
get output volume of dimension 32 x 32 x 12.
Activation Function Layer: This layer will apply element wise activation function to
the output of convolution layer. Some common activation functions are RELU: max(0,
x), Sigmoid: 1/(1+e^-x), Tanh, Leaky RELU, etc. The volume remains unchanged hence
output volume will have dimension 32 x 32 x 12.
NIIS
INSTITUTE
OF
BUSINESS
ADMINISTRATION
BHUBANESWAR
Continue…
Pool Layer:
This layer is periodically inserted in the covnets and its main functionis to reduce
the size of volume which makes the computation fast reduces memoryand also
prevents from overfitting. Two common types of pooling layers are maxpooling
and average pooling. If we use a max pool with 2 x 2 filters and stride 2,the
resultant volume will be of dimension 16x16x12.
 Fully-Connected Layer:
This layer is regular neural network layer which takesinput from the previous
layer and computes the class scores and outputs the 1-Darray of size equal to the
number of classes.
NIIS
INSTITUTE
OF
BUSINESS
ADMINISTRATION
BHUBANESWAR
Proposed System
Convolution Neural Network
Caffe Model
NIIS
INSTITUTE
OF
BUSINESS
ADMINISTRATION
BHUBANESWAR
Advantages
Highly Security
Its easily detection in mask
NIIS
INSTITUTE
OF
BUSINESS
ADMINISTRATION
BHUBANESWAR
Applications
Real time Applications
Airport
Train station
Bus stops….. etc
NIIS
INSTITUTE
OF
BUSINESS
ADMINISTRATION
BHUBANESWAR
Software Required
android studio
NIIS
INSTITUTE
OF
BUSINESS
ADMINISTRATION
BHUBANESWAR

face mask using android ppt.pptx

  • 1.
    Android Based Face MaskDetection System APU KUMAR GIRI 4TH SEMESTER MASTER OF COMPUTER APPLICATION NIIS INSTITUTE OF BUSINESS ADMINISTRATION BHUBANESWAR
  • 2.
    Abstract In order toeffectively prevent the spread of COVID-19 virus, almost everyone wears a mask during coronavirus epidemic. This almost makes conventional facial recognition technology ineffective in many cases, such as community access control, face access control, facial attendance, facial security checks at train stations, etc. Therefore, it is very urgent to improve the recognition performance of the existing face recognition technology on the masked faces. Most current advanced face recognition approaches are designed based on deep learning, which depend on a large number of face samples. However, at present, there are no publicly available masked face recognition datasets. To this end, this work proposes three types of masked face datasets, including Masked Face Detection Dataset (MFDD), Real-world Masked Face Recognition Dataset (RMFRD) and Simulated Masked Face Recognition Dataset (SMFRD). Among them, to the best of our knowledge, RMFRD is currently the world's largest real-world masked face dataset. These datasets are freely available to industry and academia, based on which various applications on masked faces can be developed NIIS INSTITUTE OF BUSINESS ADMINISTRATION BHUBANESWAR
  • 3.
    Introduction Face recognition isa promising area of applied computer vision [1]. This technique is used to recognize a face or identify a person automatically from given images. In our daily life activates like, in a passport checking, smart door, access control, voter verification, criminal investigation, and many other purposes face recognition is widely used to authenticate a person correctly and automatically. Face recognition has gained much attention as a unique, reliable biometric recognition technology that makes it most popular than any other biometric technique likes password, pin, fingerprint, etc. Many of the governments across the world also interested in the face recognition system to secure public places such as parks, airports, bus stations, and railway stations, etc. Face recognition is one of the well-studied reallife problems. Excellent progress has been done against face recognition technology NIIS INSTITUTE OF BUSINESS ADMINISTRATION BHUBANESWAR
  • 4.
    Existing System: Support VectorMachine Discrete Wavelet Transform NIIS INSTITUTE OF BUSINESS ADMINISTRATION BHUBANESWAR
  • 5.
    Drawbacks  Existing facerecognition solutions are no longer reliable when wearing a mask. Time consuming Process Poor Detection NIIS INSTITUTE OF BUSINESS ADMINISTRATION BHUBANESWAR
  • 6.
    Block Diagram Input Pre- processing Cropping Face image CNN classification obileset modelsCaff e m Database Without mask With Mask NIIS INSTITUTE OF BUSINESS ADMINISTRATION BHUBANESWAR
  • 7.
    Preprocessing Preprocessing is thedata preprocessing and data augmentation module of the Keras deep learning library. It provides utilities for working with image data, text data, and sequence data NIIS INSTITUTE OF BUSINESS ADMINISTRATION BHUBANESWAR
  • 8.
  • 9.
    Cnn classification CNN description InputLayer: This layer holds the raw input of image with width 32, height 32 and depth Convolution Layer: This layer computes the output volume by computing dot product between all filters and image patch. Suppose we use total 12 filters for this layer we’ll get output volume of dimension 32 x 32 x 12. Activation Function Layer: This layer will apply element wise activation function to the output of convolution layer. Some common activation functions are RELU: max(0, x), Sigmoid: 1/(1+e^-x), Tanh, Leaky RELU, etc. The volume remains unchanged hence output volume will have dimension 32 x 32 x 12. NIIS INSTITUTE OF BUSINESS ADMINISTRATION BHUBANESWAR
  • 10.
    Continue… Pool Layer: This layeris periodically inserted in the covnets and its main functionis to reduce the size of volume which makes the computation fast reduces memoryand also prevents from overfitting. Two common types of pooling layers are maxpooling and average pooling. If we use a max pool with 2 x 2 filters and stride 2,the resultant volume will be of dimension 16x16x12.  Fully-Connected Layer: This layer is regular neural network layer which takesinput from the previous layer and computes the class scores and outputs the 1-Darray of size equal to the number of classes. NIIS INSTITUTE OF BUSINESS ADMINISTRATION BHUBANESWAR
  • 11.
    Proposed System Convolution NeuralNetwork Caffe Model NIIS INSTITUTE OF BUSINESS ADMINISTRATION BHUBANESWAR
  • 12.
    Advantages Highly Security Its easilydetection in mask NIIS INSTITUTE OF BUSINESS ADMINISTRATION BHUBANESWAR
  • 13.
    Applications Real time Applications Airport Trainstation Bus stops….. etc NIIS INSTITUTE OF BUSINESS ADMINISTRATION BHUBANESWAR
  • 14.