Book Image

Raspberry Pi Computer Vision Programming - Second Edition

By : Ashwin Pajankar
5 (1)
Book Image

Raspberry Pi Computer Vision Programming - Second Edition

5 (1)
By: Ashwin Pajankar

Overview of this book

Raspberry Pi is one of the popular single-board computers of our generation. All the major image processing and computer vision algorithms and operations can be implemented easily with OpenCV on Raspberry Pi. This updated second edition is packed with cutting-edge examples and new topics, and covers the latest versions of key technologies such as Python 3, Raspberry Pi, and OpenCV. This book will equip you with the skills required to successfully design and implement your own OpenCV, Raspberry Pi, and Python-based computer vision projects. At the start, you'll learn the basics of Python 3, and the fundamentals of single-board computers and NumPy. Next, you'll discover how to install OpenCV 4 for Python 3 on Raspberry Pi, before covering major techniques and algorithms in image processing, manipulation, and computer vision. By working through the steps in each chapter, you'll understand essential OpenCV features. Later sections will take you through creating graphical user interface (GUI) apps with GPIO and OpenCV. You'll also learn to use the new computer vision library, Mahotas, to perform various image processing operations. Finally, you'll explore the Jupyter Notebook and how to set up a Windows computer and Ubuntu for computer vision. By the end of this book, you'll be able to confidently build and deploy computer vision apps.
Table of Contents (15 chapters)

Detecting barcodes in images

A barcode is a way that information is represented visually and is easy to understand for purpose-made machines. There are many barcode formats. The usual format has parallel vertical lines of different thicknesses and different amounts of space in between them.

In this section, we will demonstrate how to detect a simple parallel-lines formatted barcode from a still image. We will use the following image of a soda can:

Figure 11.6 – The original source image

  1. Let's read the source image of a soda can using the following code:
    import numpy as np
    import cv2
    image=cv2.imread('/home/pi/book/dataset/barcode.jpeg', 1)
    input = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
  2. The horizontal image of a barcode has a low and a high vertical gradient. So, the candidate image must have the region that fits this criterion. We will use the cv2.Sobel() function to compute the horizontal and vertical derivatives and...