Hello everyone and welcome back to the course of computer vision.

In the previous video we discussed about how we are going to organize the lectures as well

as the exercises and we also got introduced to the team.

I will be the main point of contact as well as the main lecturer who will take major rate

of the lectures.

Vincent and Mark will coordinate with me and help me out when I need their help and Prathmesh

and Darius will take care of the exercises.

In this video we are going to start talking about computer vision in general.

So I am going to do an introduction of computer vision and its related applications to you.

So let's begin.

In the introduction to computer vision I am going to start talking about mainly the application

area, commercial and research based where computer vision is heavily used and you will

be surprised.

So let's see what it's about.

These slides are not mine.

I have adopted them from James Tompkins lecture series on computer vision from Brown University

from the year 2017.

So if you want to go back and check out their slides you are welcome to do this.

Jitendra Malik is one of the pioneer, is considered one of the pioneer of computer vision and

according to him he tried to coin three R's of computer vision, recognition, reconstruction

as well as reorganization.

Instead of writing, say, let's say reading, writing and arithmetic and so on, these things

because when you think about computer vision and its real world application majority of

them encompassed by these ideas.

So that's why I guess he said that statement.

We will come back to this statement at the end of the lecture so that we reflect on whether

these statements make sense.

We already know that there are multitudes of applications for computer vision from,

for example, like in laptops when you have biometrics auto login, face recognition based

on 3D optical character recognition, such things.

Even smartphones these days have so many applications that use computer vision directly or indirectly

like your Snapchat filters or Facebook messengers tagging and the virtual optars that you create

on them.

And then there are also specialized applications on Android and iOS equally that explore or

that use computer vision algorithms heavily.

For example, panorama construction, image stitching by it is panorama construction is

done by image stitching and the software itself has inbuilt this algorithm so that you are

when you're taking the panorama, it automatically stitch stitches the images to produce a final

panoramic image.

Even on web you find a lot of applications.

For example, in Google Photos when you upload your photos there, there is object detection,

vision pipelines running behind, geolocalization or even Facebook has in its interface a lot

of vision algorithms running at the backend.

What else?

Yeah.

In the VR, virtual reality and augmented reality have also been influenced heavily by, for

example, when you see HTC Vive or even HoloLens or Microsoft also has its own virtual augmented

reality lenses.

Google also has them.

Facebook has released recently named Oculus.