Overview
Things
Story

Problem
Solution
How it works
NodeMCU
OpenCV
Python libraries
More you can do
Youtube vid

Published May 8, 2021

Python OpenCV NodeMCU Mask Detection

The system prevents you to forget the mask at home and also remind you to sanitize your hands when come come

IntermediateFull instructions provided1 hour3,862

Things used in this project

Hardware components

NodeMCU ESP8266 Breakout Board

Digilent IR Proximity Sensor

Ultrasonic Sensor - HC-SR04 (Generic)

SG90 Micro-servo motor

Jumper wires (generic)

web camera

Software apps and online services

Arduino IDE

OpenCV

Hand tools and fabrication machines

Soldering iron (generic)

Story

Problem:

so, when I go outside I forgot my mask at home then after realization, I get back home and take it
it's just a waste of time

Solution:

made a system with OpenCV to detect I'm wearing a mask or not, if I'm not wearing a mask then it will give me a mask, and also when I return at home it reminds me to sanitize my hands

How it works:

the ultrasonic sensor detects that I'm in front of the camera or not.

by using open cv and front face Haar cascade files it detects face and the by using mouth Haar cascade it detects mouth if it's able to detect face without mouth it will say that I'm wearing a mask if it detects face and mouth both then it says that I am not wearing a mask.
so if it detects that I'm wearing a mask then it just doesn't do any then and ignore it and if it detects I'm not wearing a mask the servo on the top of the gate will give me the mask hanging to it.

and when I come home an app called Automate that detects that I'm that my phone is connected to homes wifi then it posts an HTTP request to the system then the system will remind me to sanitize my hands if I don't pick up the bottle in under 30 sec then it will again remind me.

1 / 3

Automate flow to post HTTP requests when I come home.

NodeMCU:

there is a webserver running in NodeMCU that is connected to a python program via serial

1 / 2

so if the person in front of the ultrasonic sensor is then it will type H in serial then the python reads it and starts the procedure of mask or not detection if it finds that the person is not wearing a mask then it will post an HTTP request to rotate the servo to give mask on top of the gate

import serial
m5 = serial.Serial('COM5', 115200, timeout=.1)# change port as per your Nodemcu Port
while True:
	da = m5.readline()[:-2]
	if da==b'H'
           print("data recived")

python serial

OpenCV:

I'm a beginner at it
haar cascade so haar feature-based cascade classifier is a machine learning-based approach where a cascade function is trained for a lot of positive and negatives images
so by using this I can detect faces. Click here to find

import cv2

face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')

cap = cv2.VideoCapture(0)

while cap.isOpened():
    _, img = cap.read()
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    faces = face_cascade.detectMultiScale(gray, 1.1, 4)
    for (x, y , w ,h) in faces:
        cv2.rectangle(img, (x,y), (x+w, y+h), (255, 0 , 0), 3)
    cv2.imshow('img', img)
    if cv2.waitKey(1) & 0xFF == ord('q'):
              break
cap.release()

this way you can also make your own Haar cascade

so my idea is to find faces then mouth if the system is not able to find a mouth then I'm wearing a mask and if able to find a mouth and face then no mask.

1 / 2 • wearing mask

mouth Haar cascade

Python libraries:

pip install pyttsx
pip install serial
pip install opencv-python

More you can do:

you can use a raspberry pi as the onboard computer it will be a better choice as my pi is on another work.
add pump that sprays sanitizer to the whole boy when you come home.
at the last stay home stay safe.

Youtube vid:

#include <ESP8266WiFi.h>
#include <Servo.h>

const char* ssid = "ssid";
const char* password = "pass";

#define echoPin 5 
#define trigPin 4
long duration; 
int distance;
int val;
int irs = 0;
//int pump = 14;

Servo myservo;
WiFiServer server(80);

void setup() {
  WiFi.softAPdisconnect (true);
  Serial.begin(115200);
  delay(10);
  myservo.attach(2)
  myservo.write(0);
  pinMode(irs, INPUT);
  //pinMode(pump,OUTPUT);
  pinMode(trigPin, OUTPUT); 
  pinMode(echoPin, INPUT);
 
  WiFi.begin(ssid, password);
 
  while (WiFi.status() != WL_CONNECTED) {
    delay(500);
  }

  server.begin();
  
 Serial.print(WiFi.localIP());
  
}
 
void loop() {
  int irsval = digitalRead(irs);
  digitalWrite(trigPin, 0);
  delayMicroseconds(2);
  digitalWrite(trigPin, 1);
  delayMicroseconds(10);
  digitalWrite(trigPin, 0);
  duration = pulseIn(echoPin, 1);
  distance = duration * 0.034 / 2; 
  if (distance < 45){
    Serial.println('H');
    delay(2000);
  }
  WiFiClient client = server.available();
  if (!client) {
    return;
  }
 
  while(!client.available()){
    delay(1);
  }
 
  String request = client.readStringUntil('\r');
  client.flush();
  
  if (request.indexOf("/M") != -1){
    myservo.write(90);
    delay(1000);
    myservo.write(0);
  }
  else if (request.indexOf("/P") != -1)  {
    Serial.println('D');
    delay(30000);
    if(irsval==0){
      Serial.println('S');
    }
  }
  
  client.println("HTTP/1.1 200 OK");
  client.println("Content-Type: text/html");
  client.println(""); 
  client.println("<!DOCTYPE HTML>");
  client.println("<html>");
  client.println("<center>");
  client.println("<h1 style=background-color:DodgerBlue;>ATI SYSTEMS</h1>");
  client.println("</center>"); 
  client.println("</html>");
 
  delay(1);
}

import cv2
import serial
import webbrowser
import pyttsx3

engine = pyttsx3.init('sapi5')
voices = engine.getProperty('voices')
engine.setProperty('voice', voices[1].id)

def say(audio):
    engine.say(audio) 
    engine.runAndWait()
    
m5 = serial.Serial('COM8', 115200, timeout=.1)

face_cascade = cv2.CascadeClassifier('/Users/HP/Desktop/haarcascade_frontalface_default.xml')
mouth_cascade = cv2.CascadeClassifier('/Users/HP/Desktop/Mouth.xml')

cap = cv2.VideoCapture(1)

while True:
    da = m5.readline()[:-2]
    if da==b'H':
        ret, img = cap.read()
        img = cv2.flip(img,1)
        gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
        (thresh, black_and_white) = cv2.threshold(gray, 80, 255, cv2.THRESH_BINARY)
        faces = face_cascade.detectMultiScale(gray, 1.1, 4)
        faces_bw = face_cascade.detectMultiScale(black_and_white, 1.1, 4)
        for (x, y, w, h) in faces:
            cv2.rectangle(img, (x, y), (x + w, y + h), (0, 0, 255), 2)
            roi_gray = gray[y:y + h, x:x + w]
            roi_color = img[y:y + h, x:x + w]
            mouth_rects = mouth_cascade.detectMultiScale(gray, 1.5, 5)
            if(len(mouth_rects) == 0):
                print("MASK DETECTED")
            else:
                for (mx, my, mw, mh) in mouth_rects:
                    if(y < my < y + h):
                        print("NO MASK DETECTED")
                        say("sir please wear mask")
                        webbrowser.open('http://192.168.43.212/M')
                        break    
    elif da==b'D':
        say("sir please sanitize your hands")
    elif da==b'S':
        webbrowser.open('http://192.168.43.212/P')
    else:
        print("YOU ARE GREAT AJ")
    #cv2.imshow('frame',img)    
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break
cap.release()
cv2.destroyAllWindows()

Credits

Amaan Javed

19 projects • 4 followers

Student

Python OpenCV NodeMCU Mask Detection

Things used in this project

Hardware components

Software apps and online services

Hand tools and fabrication machines

Story

Problem:

Solution:

How it works:

NodeMCU:

OpenCV:

Python libraries:

More you can do:

Youtube vid:

Code

NodeMCU

Python OpenCV

Credits

Amaan Javed

Comments

Embed the widget on your own site

Python OpenCV NodeMCU Mask Detection

Python OpenCV NodeMCU Mask Detection

Things used in this project

Hardware components

Software apps and online services

Hand tools and fabrication machines

Story

Problem:

Solution:

How it works:

NodeMCU:

OpenCV:

Python libraries:

More you can do:

Youtube vid:

Code

NodeMCU

Python OpenCV

Credits

Amaan Javed

Comments

Related channels and tags