In this video, we enhance the logic to work with domain models. Learn how this improves the accuracy of the image recognition algorithm.
- [Instructor] Let's examine the last result we got.…We passed in sunset.jpg, and for some reason…the tags include things like man,…airplane,…jet,…surfing,…boat.…The confidence is only 78%.…Let's go look at that picture again.…I'm going to start debugging.…And let's go ahead and open that picture again.…I don't see a man in this picture.…Neither do I see an airplane.…So the thing is…that the quality of the result's return by AI…in general can be improved by custom domain models.…
Luckily for us, there are two models…that come out of the box with the Vision API.…One is called Celebrities, second is called Landmarks.…So, with the help of the Celebrities landmark,…we'll recognize this famous person,…whoever that might be,…and with Landmarks we'll recognize this landmark.…Okay.…I'm going to make some minor modifications to my code.…So, the first modification I'll make…is that I will accept…the model as an optional parameter into my math here…We still need to act on it, but let's say…that I wish to recognize famousperson.jpg…
- Exploring the possibilities of the Vision API
- Submitting an image to the Vision API for processing
- Asking the Vision API to recognize faces
- Working with the Speech API
- Writing speech-to-text code
- Working with the Language API
- Getting languages for translation
- Language Understanding (LUIS) concepts
Skill Level Intermediate
Creating Bots with the Microsoft Bot Framework, Part 1with Scott Peterson45m 41s Intermediate
Creating Bots with the Microsoft Bot Framework, Part 2with Scott Peterson50m 17s Intermediate
1. The Vision API
2. The Speech API
3. The Language API
Next steps1m 42s
- Mark as unwatched
- Mark all as unwatched
Are you sure you want to mark all the videos in this course as unwatched?
This will not affect your course history, your reports, or your certificates of completion for this course.Cancel
Take notes with your new membership!
Type in the entry box, then click Enter to save your note.
1:30Press on any video thumbnail to jump immediately to the timecode shown.
Notes are saved with you account but can also be exported as plain text, MS Word, PDF, Google Doc, or Evernote.