OpenCV Computer Vision Application Programming

OpenCV offers different programming interfaces. Get to know which are the possible programming languages that can be used with OpenCV.

The C interface is useful as many examples are written in it. Here we will learn the basics of it. We will also learn how to use pkg-config to compile the code.

The C++ interface is useful as it provides better memory management than the C interface. Here we will learn the basics of it. We will also learn how to compile it using CMake.

The Python interface is useful because many people are more confident with Python rather than C/C++. Also, the final code is usually shorter as compared to using C or C++. Here we will learn the basics of it.

Drawing shapes such as rectangles, lines, circles, or text is very useful when working with OpenCV. Here we will learn the basics of it.

Sometimes we need to hide some areas of an image by using OpenCV to blur it. OpenCV can also be used to smoothen parts of an image.

In image processing, sometimes we need to merge objects together, separate them, fill holes, or remove noise which can be done with image morphology.

Most of the times images need to be scaled or rotated. OpenCV allows us to perform those actions easily.

Sometimes we need to represent an image in another way to understand it better. Histograms are a great tool for that.

When you want to separate or segment data into groups you can use k-means to separate large, medium, and small images automatically, and many other applications.

Sometimes you roughly know how segmentation should be done. That is when the Watershed algorithm can help us, especially for robotics.

When we need to separate an object from a cluttered scene, we can use the Grabcut algorithm to segment it automatically.

Knowing where a specific area of an image is in another image, is very useful for many applications. Learn how to find points of an image in another one.

Landscapes or large objects usually can't be photographed in a single shot. The solution is to take pictures of parts of the scene and then merge them together using OpenCV.

Sometimes, specially when scanning photographs, small unwanted errors appear, because of dust or other problems. By using OpenCV, we can easily remove those problems.

Enhance low light images by learning how to equalize the histograms so that the average brightness is increased as well as the contrast, resulting in brighter images.

Learn how to display an image that has more than 8 bits per channel by using OpenCV to read an HDR image.

Use OpenCV to locate a specific logo or other simple shapes in your image very easily with its Chamfer Matching functionality.

Learn how to use OpenCV to detect faces, or other objects in your images, such as eyes.

Use specific features and a detector that is suited for automatic people-detection with OpenCV, in order to detect people in images.

Detecting objects in OpenCV is great when your objects are already trained, but when we need to detect something else we need to create a new cascade.

You may want to automatically identify a person. With OpenCV you can compare it to a database of known faces using Fisherfaces.

With a calibrated camera, we can reduce those distortions, and create a better image using OpenCV.

Remove or reduce the distortion of an image.

Sometimes we may need to see a wall or floor of an image as if we were standing in front of them. You can do that by doing a perspective transform.

Calibrate and rectify our stereo images.

We may need to know about the position of the objects of your scene. We can do that by generating a disparity image.