Watson Developer Cloud

Getting started with the Visual Insights service


All instances of the IBM Watson™ Visual Insights service are deprecated as of May 30, 2016. The service will be removed on July 13, 2016. To continue using cognitive vision functionality in your app, check out the IBM Watson™ Visual Recognition service.


The IBM Watson™ Visual Insights service provides an Application Programming Interface (API) that enables you to upload a set of images as a zip file for visual insight extraction. Visual Insights turns a collection of images into structured data that can easily be indexed and queried, helping you understand the interests, activities, hobbies, life events, and product themes in the images. The service applies classifiers built on machine-learning technology to the images' pixels to generate a set of scores for various visual aspects of the images, aggregated across the set of uploaded images.

The service returns a summary of the image set's visual attributes. The summary consists of a JSON array of labels, each with a score between 0 and 1. A higher score indicates a higher relevance of the label for the input image set.

You can see a quick demo of the Visual Insights service in action. The demo lets you test collections of images to determine their visual attributes.

You can submit comments or ask questions about Visual Insights in the Watson forum. You can also read posts about Watson services that are written by IBM researchers, developers, and other experts on the Watson blog.

For a language-independent introduction to working with Watson Developer Cloud services and Bluemix, see Developing Watson applications with Bluemix. That page provides an overview of working with Watson services with the Bluemix web interface, the Eclipse IDE, or the Cloud Foundry command-line tool.

Learning more about the service

For more information about the Visual Insights service, see the following sections: