Developers

Build unique visual recognition apps with Watson: 4 easy ways to get started

Share this post:

Key Points:
– You can use the Watson Visual Recognition API service in your apps to understand the contents of images.
– You can even train Watson to recognize specialized image content that relates to a particular industry.
– Watson offers videos, tutorials, demos, technical documentation and guides to help you get started.

Try our Visual Recognition API

 

You can use the IBM Watson Visual Recognition API service in your apps to understand the contents of images, such as faces. You can even train Watson to recognize specialized image content that relates to a particular industry. Right now, Visual Recognition is helping geoinformatics company OmniEarth combat drought in California, social media analytics firm iTrend analyze unstructured social media data and fashion designer Jason Grech understand fashion trends.

At the Watson Visual Recognition home page, you can find out more about the API, try a demonstration, and go through links to helpful information. People learn in different ways, so here’s a list of resources you can use no matter what your preferred learning style may be.

1. Documentation for linguistic learners

The Watson APIs have extensive documentation to help you start using the Watson services and set up your environment on the IBM cloud platform. In the Visual Recognition section, you’ll find tutorials and extensive documentation:

2. Diagrams and code examples for visual learners

To get a visual overview of the architecture and use cases that show you how you might use the Visual Recognition API, check out the Visual Recognition Overview page. You also can:

  • Run through the demonstration of the BluePic application, which lets you share photos with other BluePic users. The app uses a Kitura-based server application written in Swift in a mobile iOS application.
  • Read this blog post about how you can create custom classifiers to train the Visual Recognition service to recognize specific content within your images and get sample code.

3. Videos and webinars for aural learners

If you like to learn by listening, the Building With Watson series is a great resource for techniques on how to get the most from Watson. For Visual Recognition, check out these webinars and videos:

4. Sample applications and API Explorer for physical learners

When you want to get down into the code, check out these resources:

Find answers to all your “Visual Recognition” questions 

As you’re learning and experimenting with Visual Recognition, if you run into questions or have comments, you can share them in our developerWorks forums. For more answers, you can check out these developer communities as well:

  • The Watson forums on Stack Overflow.
  • The Watson forum on dW Answers.

Ready to get started? Try it out on Bluemix now.

Try Watson Visual Recognition with our free 30-day trial

 

Senior Writer, IBM Watson

More Developers stories
March 18, 2019

Women of Watson Part 2: Meet Laura Donaldson

In honor of Women’s History Month for the month of March, we’re continuing our Women of Watson series. This week, we’re featuring IBM Watson Marketing Leader Laura Donaldson. Prior to her career at IBM, Laura was an Emmy-winning broadcaster in Arizona, as well as a public relations manager in New York. Get to know Laura Donaldson.

Continue reading

March 8, 2019

Women of Watson Part 1: Meet Jennifer Sukis

Today on International Women’s Day, we’re thrilled to roll out a four-part Women of Watson series. To commemorate Women’s History Month, each week in March we will highlight a woman working at IBM Watson who has helped to shape Watson as the AI for the business professional.

Continue reading

March 5, 2019

Use intelligent search to find real answers with less effort with Watson Discovery

Introducing, smart document understanding (SDU), a powerful feature now available in Watson Discovery, that can give you accurate answers faster, from 10 days to 2 minutes for one leading bank. Building on advances from IBM Research and drawing on the corpus conversion service released in late 2018, smart document understanding allows you visually train AI to understand your documents.

Continue reading