Month: February 2021

import cv2
import sys
facecascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
video_capture = cv2.VideoCapture(0)

while True:
    # Capture frame-by-frame
    ret, frame = video_capture.read()
    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
    faces = facecascade.detectMultiScale(
        gray,
        scaleFactor=1.1,
        minNeighbors=5,
        minSize=(30, 30),
        flags=cv2.CASCADE_SCALE_IMAGE
    )

    # Draw a rectangle around the faces
    for (x, y, w, h) in faces:
        cv2.rectangle(frame, (x, y), (x+w, y+h), (0, 255, 0), 2)
        crop_face = frame[y:y + h, x:x + w]
    # save faces
        cv2.imwrite(str(x) + '_' + str(y) + '_face.jpg', crop_face)
    # Display the resulting frame
    cv2.imshow('Video', frame)

    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

# When everything is done, release the capture
video_capture.release()
cv2.destroyAllWindows()

Run it with python sample.py, it will popup your webcam window and do face detection, you can type “q” to quit.

1. install opencv
   pip install opencv-python
2. Face detection using Haar cascades is a machine learning based approach where a cascade function is trained with a set of input data. OpenCV already contains many pre-trained classifiers for face, eyes, smiles, etc.. Today we will be using the face classifier. You can experiment with other classifiers as well.
   You need to download the trained classifier XML file (haarcascade_frontalface_default.xml), which is available in OpenCv’s GitHub repository. Save it to your working location.
3. download logo.jpg from internet

4. python3 code to detect faces in image

import cv2
# Load the cascade
#face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + "haarcascade_frontalface_default.xml")
# Read the input image
img = cv2.imread('logo.jpg')
# Convert into grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# Detect faces
faces = face_cascade.detectMultiScale(gray, 1.1, 4)
# Draw rectangle around the faces
for (x, y, w, h) in faces:
    cv2.rectangle(img, (x, y), (x+w, y+h), (255, 0, 0), 2)
    crop_face = img[y:y + h, x:x + w]
    # save faces
    cv2.imwrite(str(x) + '_' + str(y) + '_face.jpg', crop_face)
# Display the output
cv2.imshow('img', img)
cv2.imshow("imgcropped", crop_face)
cv2.waitKey()

5. run it with pythoh cv2_sample.py, you will find faces detected and cropped faces saved:

1. install Apache and WSGI
   sudo apt install apache2 libapache2-mod-wsgi-py3 python3-pip python3-virtualenv
   sudo pip3 install flask (skip this if you are planning to setup venv)
2. enable mod_wsgi
   sudo a2enmod wsgi
3. create files as below (the __init__.py and wsgi file are mandatory)

4. create apache wsgi conf file /etc/apache2/sites-available/flaskhelloworldsite.com.conf
and enable it: $ sudo a2ensite flaskhelloworldsite.com.conf

<VirtualHost *:80>
    ServerAdmin webmaster@flaskhelloworldsite.com
    ServerName 192.168.0.51
    ServerAlias flaskhelloworldsite.com
    ErrorLog /var/www/flaskhelloworldsite.com/logs/error.log
    CustomLog /var/www/flaskhelloworldsite.com/logs/access.log combined

    WSGIDaemonProcess helloworldapp user=www-data group=www-data threads=5
    WSGIProcessGroup helloworldapp
    WSGIScriptAlias / /var/www/FLASKAPPS/helloworldapp/helloworldapp.wsgi
    <Directory /var/www/FLASKAPPS/helloworldapp>
        Order allow,deny
        Allow from all
    </Directory>
</VirtualHost>

5. create log directory
$ sudo mkdir -p /var/www/flaskhelloworldsite.com/logs
$ sudo chown -R www-data:www-data flaskhelloworldsite.com

6. restart apache and verify the app
systemctl restart apache2
then you can open http://192.168.0.51/

NOTE: if you want use python virtual env, we can setup venv in /var/www/FLASKAPPS:
virtualenv venv
source venv/bin/activate
pip install flask
then update WSGIDaemonProcess in /etc/apache2/sites-available/flaskhelloworldsite.com.conf with python-home:
WSGIDaemonProcess helloworldapp user=www-data group=www-data threads=5 python-home=/var/www/FLASKAPPS/venv

1. create hello.py with class User(db.Model)

from flask import Flask
from flask_sqlalchemy import SQLAlchemy
app = Flask(__name__)
 
app.config['SQLALCHEMY_DATABASE_URI'] = 'sqlite:///users.sqlite3'
app.config['SECRET_KEY'] = "op23413kjkjljlksjfaksjfdlksajfkjlkjlkjk"
app.config['SQLALCHEMY_TRACK_MODIFICATIONS'] = False
db = SQLAlchemy(app)
 
class User(db.Model):
    __tablename__ = 'users'
    username = db.Column(db.String(64), primary_key=True)
    passwd = db.Column(db.String(64))
    def __repr__(self):
        return '<User %r>' % self.username
 
if __name__ == "__main__":
        db.create_all()
        app.run("0.0.0.0", 8090, debug=True)

2. test hello.py with python3 shell

zhub2@apache-vm1:~ $ python3
>>> from hello import db
>>> db.create_all()
>>> from hello import User
### INSERT NEW User
>>> user_john = User(username='john', passwd='carlos23')
>>> db.session.add(user_john)
>>> db.session.commit()
### LIST ALL User
>>> User.query.all()
[<User 'john'>]
### UPDATE User WHERE username='john'
>>> user_john = User.query.filter_by(username='john').first()
>>> user_john.passwd='test123'
>>> db.session.add(user_john)
>>> db.session.commit()