Summary

In this chapter, we explored the basics of object segmentation in a controlled situation where a camera takes pictures of different objects. Here, we learned how to remove background and light to allow us to binarize our image better, thus minimizing the noise. After binarizing the image, we learned about three different algorithms that we can use to divide and separate each object of one image, allowing us to isolate each object to manipulate or extract features.

We can see this whole process in the following image:

Finally, we extracted all of the objects on an image. You will need to do this to continue with the next chapter, where we are going to extract characteristics of each of these objects to train a machine learning system.

In the next chapter, we are going to predict the class of any objects in an image and then call a robot or any other system to pick any of them, or detect an object that is not in the correct carrier tape. We will then look at notifying a person to pick it up.