Raspberry Pi Cookbook, 4th Edition

Chapter 8. Computer Vision

8.0 Introduction

Computer vision (CV) allows your Raspberry Pi to “see” things. In practical terms, this means that your Raspberry Pi can analyze an image, look for items of interest, and even recognize faces and text.

If you connect a Raspberry Pi to a camera to supply the images, all sorts of possibilities open up. This theme is continued in Chapter 9 where we take this a stage further into the realm of machine learning.

8.1 Installing OpenCV

Problem

You want to install OpenCV computer vision software on your Raspberry Pi.

Solution

To install OpenCV, first install the prerequisite packages and update the NumPy Python library using these commands:

$ sudo apt install libatlas-base-dev
$ pip3 install --upgrade pip
$ pip3 install imutils
$ pip3 install numpy --upgrade

Then install OpenCV itself using:

$ pip3 install opencv-python

After installation is complete, you can check that everything is working by starting Python 3, importing cv2, and checking the version:

$ python3
Python 3.9.2 (default, Mar 12 2021, 04:06:34) 
[GCC 10.2.1 20210110] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import cv2
>>> cv2.__version__
'4.6.0'
>>> 
>>> exit()

Note that __version__ is the word “version” with two underscore characters on each side.

Discussion

Computer vision is both processor and memory intensive, so although OpenCV will just about work on an older Raspberry Pi, it can be slow on anything earlier ...