Book Image

Getting Started with Python for the Internet of Things

By : Tim Cox, Steven Lawrence Fernandes, Sai Yamanoor, Srihari Yamanoor, Prof. Diwakar Vaish
Book Image

Getting Started with Python for the Internet of Things

By: Tim Cox, Steven Lawrence Fernandes, Sai Yamanoor, Srihari Yamanoor, Prof. Diwakar Vaish

Overview of this book

This Learning Path takes you on a journey in the world of robotics and teaches you all that you can achieve with Raspberry Pi and Python. It teaches you to harness the power of Python with the Raspberry Pi 3 and the Raspberry Pi zero to build superlative automation systems that can transform your business. You will learn to create text classifiers, predict sentiment in words, and develop applications with the Tkinter library. Things will get more interesting when you build a human face detection and recognition system and a home automation system in Python, where different appliances are controlled using the Raspberry Pi. With such diverse robotics projects, you'll grasp the basics of robotics and its functions, and understand the integration of robotics with the IoT environment. By the end of this Learning Path, you will have covered everything from configuring a robotic controller, to creating a self-driven robotic vehicle using Python. • Raspberry Pi 3 Cookbook for Python Programmers - Third Edition by Tim Cox, Dr. Steven Lawrence Fernandes • Python Programming with Raspberry Pi by Sai Yamanoor, Srihari Yamanoor • Python Robotics Projects by Prof. Diwakar Vaish
Table of Contents (37 chapters)
Title Page
Copyright and Credits
About Packt
Contributors
Preface
Index

Building a face detector application


In this section, we discuss how human faces can be detected from webcam images. A USB webcam needs to be connected to Raspberry Pi 3 to implement real-time human face detection.

How to do it...

  1. Import the necessary packages:
import cv2 
import numpy as np 
  1. Load the face cascade file:
frontalface_cascade= cv2.CascadeClassifier('haarcascade_frontalface_alt.xml') 
  1. Check whether the face cascade file has been loaded:
if frontalface_cascade.empty(): 
  raiseIOError('Unable to load the face cascade classifier xml file') 
  1. Initialize the video capture object:
capture = cv2.VideoCapture(0) 
  1. Define the scaling factor:
scale_factor = 0.5 
  1. Perform the operation until the Esc key is pressed:
# Loop until you hit the Esc key 
while True: 
  1. Capture the current frame and resize it:
  ret, frame = capture.read() 
  frame = cv2.resize(frame, None, fx=scale_factor, fy=scale_factor,  
            interpolation=cv2.INTER_AREA) 
  1. Convert the image frame into grayscale:
  gray_image = cv2.cvtColor...