Original subtitles

So let's talk a bit about how images are formed.

So we're going to look at the most basic example of an image formation onto a piece of film.

So imagine you're all tied in a park and you're holding a strip of film while facing a tree so light

reflects off the tree at different points and bounces off a tree onto your piece of film.

So as you can see in this example what happens here is at the top of the tree and the middle of a tree

are going to reflect at similar points along the fall.

That's not good.

That Blatchley focus will basically result in an unfocused image or blurred image here.

So as we can see that's not how our eyes or cameras work.

This is a best example of how our eyes and cameras work.

We essentially use a barrier to block off most points of light while leaving a small gap here and that

gap has called aperture and discloses some points of light to be reflected onto the film.

So this gives you a much more focused image and that's actually the basis of a pinhole camera.

So it is a problem with a simple pinhole camera model and the aperture is always fixed.

So that means that a constant amount of light is always entering this hall which can be sometimes overpowering

for the film.

Meaning that everything is going to look white.

And secondly we can focus using a fix up at you to focus the image even better although it's never going

to be as bad as the previous image.

We still need to move the film back and forth.

And that's not really a good system.

So how do we fix this.

Well and by using a lens and an adaptive lens which is what most modern cameras and our eyes use it

allows us to control the aperture size and in photography aperture size is referred to as f stops and

cameras and lower is better and also allows us to get some nice depth of field which is also called

booka in photography.

Just so you know Booker is a highly desirable trait in photography.

It allows us to have very blurred back drawings while we focus on a foreground image resulting in a

pretty nice effect.

Secondly though with using a lens you actually can control the lens with which allows us to instead

of moving the film back and forth.

We actually use a lens to focus directly on this point here.

This results in a very nice nicely controlled system so fiercely before discussing how computers do

images.

I think it's good to discuss how humans see images and it is one thing you should know humans are exceptionally

good at Image Processing starting with our eyes.

They're remarkably good at focusing quickly seeing in varying light conditions and picking up sharp

details and then in terms of it to printing what we see humans are exceptional at this as we can quickly

understand the context of different images and quickly identify objects faces you name it we can actually

do this far better than any computer vision technique right now.

And our brain our brains do this by using six layers of visual processing that you can see here.

I want to go into the details of this but it's incredibly complicated and if you're curious you can

visit the Wikipedia page on our visual system right here.