It really doesn't matter whether you are trying to build a computer vision application to perform highly complex tasks, such as object detection in real-time, or simply modifying an input image in one way or another. Almost inevitably, you'll have to apply a certain type of filter to your input or output images. The reason for this is quite simple—not all pictures are ready to be processed out of the box, and most of the time, applying filters to make images smoother is one of the ways to make sure they can be fed into our algorithms.

The variety of filters that you can apply to your images in computer vision is huge, but in this section, we're going to be learning about some of the most important filters and especially the ones with an implementation in the OpenCV library that we can use.