In a previous blog, we looked at the new 3-part course for developers on developerWorks titled, “Create Swift mobile apps with IBM Watson services.” We dug into the first tutorial, which extends a Swift-based, cognitive mobile app using the Alchemy API. Now we will focus on the second tutorial and how you can use the Visual Recognition service.
The video above shows that building Swift-based, mobile apps leveraging visual recognition doesn’t have to be difficult. The process is accelerated in the video, but the steps in the tutorial are easy to follow. The challenge is providing the right kind of content and data to analyze against to enable the app to work well.
Visual Recognition enables you to build in functionality to find meaning in visual content. It allows you to develop smart apps which can analyze the visual content of images or video frames. And then understand what is happening in a scene.
This simple Visual Recognition Demo shows how the service works. In it you can compare a selected or submitted image against a database of known images and image types. As you can see, the service uses known information to score and identify the most likely matches. Using additional data, you can improve the accuracy and extend its utility.
This is quickly becoming a very important and popular functionality in Internet of Things apps. Objects such as drones are being used to inspect items. Comparing images and video captured against previous images and/or video on file or in a database. A good example of this is shown in this video featuring Andy Trice, a Technical Product Manager at IBM.
In the video, Andy discusses his demo showing how insurance companies could use a drone to inspect a property. Then analyze images or video captured using a camera mounted on the drone. Imagine being able to quickly and safely assess the condition of a house or bridge after a hurricane or other type of storm.
Leveraging the power of visual recognition, the potential use cases are countless. The question is, how will you use it?
In the part 3 of this blog series, we will discuss the Speech to Text service and tutorial.