What is Watson Visual Recognition?

Watson Visual Recognition makes it easy to extract thousands of labels from your organization’s images and detect for specific content out-of-the-box. You can also build custom models to detect for specific content in images inside your applications.


Classify your images

Understand an image’s content out-of-the-box. Our pre-trained models enable you to analyze images for objects, colors, food, explicit content and other subjects for insights into your visual content.

Train with less data

Build a custom model with less training data and still achieve high accuracy.

Object Detection

Train a model to locate, count and understand relative size of multiple different objects.

Why Watson for Visual Recognition?

Easy Custom Training

Quickly label images and train a model with Watson Studio’s easy to use training experience.

Visually Inspect Anything

With a few images, train a computer vision model to detect damage on cars or parts of a circuit board using Watson Studio — a free workspace where you can create, test, and manage your custom models.

Bring AI into iOS apps with Core ML

With Watson Visual Recognition for Core ML, you can build computer vision mobile apps with no downtime. Get started with Watson Studio to build, test, and deploy your own custom models to iOS.

Autoglass® BodyRepair

Belron brand Autoglass® BodyRepair applied Watson Visual Recognition to its website’s booking page, which visually analyzes customer photos of vehicle damage and automatically recommends a repair price. The result is a 70% improvement in quote processing times by using AI analyses to determine repair costs.

Learn more

man taking a picture of crashed car
Engineer analysing a big tank with a unknown substance within.

Coca Cola + IBM

Field technicians used Watson Visual Recognition with Core ML to diagnose and correct problems on-site with little or no network connectivity. With the AI capabilities of Watson Visual Recognition and Core ML, relevant information is put directly into a tech's hands the moment they need it, to resolve issues quickly and efficiently.

Learn more


With Watson Visual Recognition, Pulsar can look beyond image captions for a more in-depth understanding of the way audiences interpret and respond to imagery. As a result, this drives brand performance by drawing new insights from previously untapped sources.

Learn more

five people up standing looking to cellphones and notebooks

Get started now with Watson Visual Recognition

Give your application the eyes to process visual information easily today