How Computer Vision Works

How Computer Vision Works

The Google Cloud Vision and Video Intelligence APIs give you access to a pre-trained machine learning model with a single REST API request. But what do those pre-trained models look like behind the scenes? In this video we’ll uncover the magic of computer vision models by breaking down how Convolutional Neural Nets work under the hood, and we’ll end with a live demo of the Vision API.

Learn more here!
How CNNs work → https://goo.gl/W51CGk
How RNNs work → https://goo.gl/I7RChj
Cloud Vision API → https://goo.gl/1OGqoC
Cloud Video Intelligence API → https://goo.gl/p2X9xn

Subscribe to the Google Cloud Platform channel → https://goo.gl/S0AS51

39 Comments

  1. Kevin Cho on March 18, 2020 at 1:58 pm

    Thank you for sharing this cool video! 👨🖐



  2. Gregor Samsa on March 18, 2020 at 1:58 pm

    This lady makes me feel a bit uncomfortable with her creepy facial mimic, but I appreciate the content.



  3. Amirali Sa on March 18, 2020 at 2:01 pm

    I wouldn’t think i’d be interested in this



  4. Studio1618 on March 18, 2020 at 2:01 pm

    Thanks, Sara. Your video is very helpful to me.



  5. C 4 Code on March 18, 2020 at 2:01 pm

    just get it now thanks to you



  6. fiza mukhtar on March 18, 2020 at 2:01 pm

    Anyone suggest me the latest research topic in computer vision



  7. Artin Bogdanov on March 18, 2020 at 2:02 pm

    Very nicely explained. Thanks a lot!



  8. Luis M on March 18, 2020 at 2:02 pm

    Excellent video!



  9. Dallas Kelley on March 18, 2020 at 2:04 pm

    This is amazingly inefficient and a surprisingly dumb way to go about image detection.



  10. Float Circuit on March 18, 2020 at 2:10 pm

    Building your own computer vision system is, frankly, much more satisfying. And you control every aspect of the technology.



  11. Float Circuit on March 18, 2020 at 2:11 pm

    Wow, the model you called a Recurrent Neural Network sounds like a flavor of a project I’m working on. Thanks, I didn’t know there was a name for it ☺️



  12. Saurabh Saneja on March 18, 2020 at 2:13 pm

    It was awesome.. thanks Google.. please let her do more machine learning tutorials.. she’s amazing at that



  13. John Lin on March 18, 2020 at 2:15 pm

    i don’t see the creative power in evolution



  14. Ashish Awasthi on March 18, 2020 at 2:15 pm

    Thanks Sara for simple explanation of computer vision and API details. A small correction though, evolution of vision as per https://en.wikipedia.org/wiki/Cambrian#Dating_the_Cambrian was less than "billions of years ago".



  15. DO YEOP KIM on March 18, 2020 at 2:16 pm

    Even I starts my master’s course in CV soon, I couldn’t explain CV in my speak. This video gave me a help to organize what is CV and how it works!



  16. Roxana Noelia on March 18, 2020 at 2:18 pm

    Great great video



  17. Aman Raj on March 18, 2020 at 2:19 pm

    Awesome



  18. Sans Techie _Official on March 18, 2020 at 2:24 pm

    You’re just training your model with million users photos , if not how can you train it to that much extent … You guys have large computing power and million users data that’s why it’s possible to train your model quickly…



  19. TCS LS - The Design Lab on March 18, 2020 at 2:25 pm

    Really digging this video. We would like to use this within our organization for a business transformation course, with your permission of course!



  20. Manikandan S on March 18, 2020 at 2:25 pm

    Gina Linetti left 99 to join GCP



  21. Swayam Rout on March 18, 2020 at 2:25 pm

    Computer vision enthusiasts pls comment below to collaborate and work on a project



  22. fiza mukhtar on March 18, 2020 at 2:26 pm

    Nice



  23. Float Circuit on March 18, 2020 at 2:28 pm

    You know how a little kid might see a cat 🐈 one time and in the future it’ll be able to tell that other cats are cats. And one day it sees a dog and can immediately tell that something’s different. That’s what I’m interested in: how do we cut down the data requirement from billions of examples to just one or two? Imagine a self driving car that could appreciate context in real-time despite not having a really fine tuned Neural net that’s based on a crazy amount of brittle test data. That’s what I’m working on as the founder of an extremely early, unnamed startup. If we don’t need 5 billion examples of cars being driven to do a good job, neither should machines. We need to build machines like babies that see cats running and just "get it". That’s the dream.



  24. Megatron on March 18, 2020 at 2:29 pm

    Honestly, Google didn’t get the data. Google gave us Google photos with unlimited storage and we uploaded millions of photos from millions of users. You got us free photos backup to we give you billions of photos to analyse.



  25. 7906jun on March 18, 2020 at 2:29 pm

    Amazing !!



  26. smraghu81 on March 18, 2020 at 2:29 pm

    Does any one knows what software they used to prepare this video. Kindly suggest.



  27. Joel Jacob on March 18, 2020 at 2:34 pm

    I loved the video



  28. Amirali Sa on March 18, 2020 at 2:35 pm

    This is amazing



  29. Leonardo Rivillini on March 18, 2020 at 2:36 pm

    hahah very happy person, no ? :´p



  30. Anthony Silva on March 18, 2020 at 2:38 pm

    What is the best programming language to learn for computer vision? I’m a college student who is fairly proficient in C++ but am not sure if I should focus more on learning Java or Python to increase my chances of landing a job working in this field after college. I’m an applied mathematics major and have taken several classes in linear algebra, real analysis, complex analysis, probability, numerical analysis/methods and differential equations.



  31. Benjamin Thomas on March 18, 2020 at 2:38 pm

    sheepdogs and mops LOL!



  32. DINGKANG WANG on March 18, 2020 at 2:38 pm

    Computer vision is not just Machine learning ok? This video gives me a feeling machine learning is the only way how computer vision works.



  33. Adam Smith on March 18, 2020 at 2:48 pm

    I loved the explanation, but I still would rather build and train my own model.



  34. patrizia casini on March 18, 2020 at 2:49 pm

    E’ STATO VERAMENTE INTERESSANTE



  35. abooda Aboood on March 18, 2020 at 2:50 pm

    Please download the translation in Arabic



  36. Denis TRUFFAUT on March 18, 2020 at 2:50 pm

    Highly professional video.
    Just miss an explanation on human labelling assisted by Google (billed or free feature ?)



  37. Karan Acharya on March 18, 2020 at 2:53 pm

    I loved the sound design here.



  38. Off/Load on March 18, 2020 at 2:54 pm

    Thank You Sara Robinson!



  39. Jon Deaton on March 18, 2020 at 2:54 pm

    viridis <3