When working with images, some of the most basic operations that are essential to get a grip on include reading the images from disk, displaying them, accessing their pixel values, and converting them from one color space to another. This tutorial explains these basic operations, starting first with a description of how a digital image is formulated in terms of its spatial coordinates and intensity values.  In this tutorial, you will familiarise yourself with the most basic OpenCV operations that […]

Digital videos are close relatives of digital images because they are made up of many digital images sequentially displayed in rapid succession to create the effect of moving visual data.  The OpenCV library provides several methods to work with videos, such as reading video data from different sources and accessing several of their properties. In this tutorial, you will familiarise yourself with the most basic OpenCV operations essential when working with videos.  After completing this tutorial, you will know: How […]

When you work with OpenCV, you most often work with images. However, you may find it useful to create animation from multiple images. Chances are that showing images in rapid succession may give you different insight or it is easier to visualize your work by introducing a time axis. In this post, you will see how to create a video clip in OpenCV. As an example, you will also learn some basic image manipulation techniques to create the images. In […]

In a previous tutorial, we explored using the k-means clustering algorithm as an unsupervised machine learning technique that seeks to group similar data into distinct clusters to uncover patterns in the data.  So far, we have seen how to apply the k-means clustering algorithm to a simple two-dimensional dataset containing distinct clusters and the problem of image color quantization.  In this tutorial, you will learn how to apply OpenCV’s k-means clustering algorithm for image classification.  After completing this tutorial, you […]

The OpenCV library has a module that implements the k-Nearest Neighbors algorithm for machine learning applications.  In this tutorial, you will learn how to apply OpenCV’s k-Nearest Neighbors algorithm for classifying handwritten digits. After completing this tutorial, you will know: Several of the most important characteristics of the k-Nearest Neighbors algorithm. How to use the k-Nearest Neighbors algorithm for image classification in OpenCV. Kick-start your project with my book Machine Learning in OpenCV. It provides self-study tutorials with working code. […]

In the world of computer vision and image processing, the ability to extract meaningful features from images is important. These features serve as vital inputs for various downstream tasks, such as object detection and classification. There are multiple ways to find these features. The naive way is to count the pixels. But in OpenCV, there are many routines to help you extract features from an image. In this post, you will see how OpenCV can help find some high-level features. […]

In the previous post, you learned some basic feature extraction algorithms in OpenCV. The features are extracted in the form of classifying pixels. These indeed abstract the features from images because you do not need to consider the different color channels of each pixel, but to consider a single value. In this post, you will learn some other feature extract algorithms that can tell you about the image more concisely. After completing this tutorial, you will know: What are keypoints […]

Besides the feature descriptor generated by SIFT, SURF, and ORB, as in the previous post, the Histogram of Oriented Gradients (HOG) is another feature descriptor you can obtain using OpenCV. HOG is a robust feature descriptor widely used in computer vision and image processing for object detection and recognition tasks. It captures the distribution of gradient orientations in an image and provides a powerful representation invariant to changes in illumination and shadowing. In this post, you will learn about HOG. […]