Welcome to our recap post for Watson Visual Recognition IBM Code Patterns! In this post I will cover what Watson Visual Recognition is, what it can be used for, and a list of IBM Code Patterns that you can check out.
What is Watson Visual Recognition?
Watson Visual Recognition is used to quickly and accurately tag, classify and search visual content using machine learning. It is available as an IBM Cloud service and can be configured via a web interface, API calls, or several SDKs.
So, what can you use Watson Visual Recognition for?
- Analyze and process video clips
- Leverage built-in classifiers for scenes, objects, faces, colors and food
- Create and train your own custom classifier
IBM Code Patterns related to Watson Visual Recognition
If you’re unfamiliar with IBM Code Patterns, they are reproducible examples that are hosted on Github and free to use (they often work on IBM Cloud’s free-tier too!). They contain detailed documentation on how to deploy and run the application, and a video to explain things. Below are the patterns we released in 2017 that relate to Watson Visual Recognition.
What to expect in 2018?
Expect more Code Patterns for Watson Visual Recognition for more custom classifiers that relate specifically to industry segments, and more fun examples like sorting waste and integrating Watson Visual Recognition with other Watson services. If you’re interested in reading more about IBM Code Patterns check out my other blogs about Watson Discovery, Watson Conversation, Watson Data Platform, and PowerAI.
Hope you enjoyed reading, happy hacking!