Computer vision is a type of machine learning that teaches computers to see like humans do.

The human eye takes in light and transmits that information to a specialized part of the brain that analyzes that signal and converts it into useful visual information. So, for computer vision, think of the camera as the eye, and the AI model as the specialized part of the brain. That’s what we’re working together to build: AI that can process light as digital information and turn that into useful visual information.

To do this, there’s an entire field of research interested in creating something called a neural network—basically a digital approximation of how the neurons in your own brain work. All of this can be pretty technical but think of it this way: the neural network is like a cake recipe. It’s the base-level set of instructions for how to make the cake. There are lots of cake recipes out there in the world (some better than others), but anyone can create their own, because the basic steps to making a cake are generally the same, no matter what.

Following this analogy, the platform lets you take our pre-written cake recipes and add your own special tweaks and finishing touches, based on your tastes. Maybe you’d prefer a cake with extra frosting in between the layers, or maybe you don’t like sprinkles. In essence, that’s what you’re doing on our platform: taking our copy of the computer vision “recipe” and updating it to your own needs and situation.

Check out our article on the three types of computer vision to learn more about how these “recipes” get put into action.