IBM Watson™ Ideas

Welcome to the IBM Watson™ Ideas Portal

We welcome and appreciate your feedback on IBM Watson™ Products to help make them even better than they are today!

If you are looking for troubleshooting help or wondering how to use our products and services, please check the IBM Watson™ documentation. Please do not use the Ideas Portal for reporting bugs - we ask that you report bugs or issues with the product by contacting IBM support.

Before you submit an idea, please perform a search first as a similar idea may have already been reported in the portal.

If a related idea is not yet listed, please create a new idea and include with it a description which includes expected behavior as well as why having this feature would improve the service and how it would address your use case.

Multiple Object Detection

Features such as custom classifiers and general tagging don't work well when there's multiple objects within a scene, or the objects that need to be classified take up less than 1/3rd of the area of an image.

  • Kevin Gong
  • Sep 28 2017
  • Needs review
Why is it useful?
Who would benefit from this IDEA? As a user, I want to be able to detect and classify multiple objects within the same image.
How should it work?
Idea Priority High
Priority Justification
Customer Name
Submitting Organization
Submitter Tags
  • Attach files
  • Derek Carroll commented
    January 25, 2018 13:59

    Hi Kevin,

    Can I clarify whether this would then allow us to classify images based on one element in the image, rather than looking at the image as a whole.

    I am thinking of our "Finger and Coin" problem at Belron GLass Repair. If the glass cracks  you're trying to classify all contain images of a finger and a coin, then this skews you data. However using this functionality would allow you place a bounding box around the damage, crop the image, then do the classification. Have I got this right, or is there another function needed for this.


    I see it's scheduled for end Feb- any chance we can get our hands on it for testing beforehand?