Background
Member Login
menu

IBM Watson Can Understand What's Inside A Photo. Guessing With Great Accuracy

IBM Watson

The American multinational technology company IBM has announced that its Artificial Intelligence Watson was getting image recognition earlier in 2016.

Now IBM is allowing the public to use Watson's ability by feeding it their own own photos to see what it thinks of them.

According to IBM on its website:

Visual Recognition allows users to understand the contents of an image or video frame, answering the question: "What is in this image?" Submit an image, and the service returns scores for relevant classifiers representing things such as objects, events and settings. What types of images are relevant to your business? How could you benefit from understanding and organizing those images based on their contents? With Visual Recognition, users can automatically identify subjects and objects contained within the image and organize and classify these images into logical categories. Need to train Visual Recognition on specific or custom content? Easily train a new classifier by sending examples and voila! Custom image recognition!

The visual recognition demo by IBM allows people to give Watson an image URL, or to upload a photo to it. Watson then return seconds later with a result showing what it thinks it sees.

And come to think of it, it's impressive, surprising and indeed scary.

Watson - image recognition

IBM's Watson is a technology platform that uses natural language processing and machine learning to reveal insights from large amounts of unstructured data. The demo is meant to show what its AI is capable of in recognizing images.

Users can also train Watson by uploading photos in bulk and classifying them. With this method, Watson can learn certain classifications. To do this, users need to upload more than 50 photos so it can learn. After each learning process, Watson should be better in identifying things

The technical demonstration is available as an open-source project on GitHub. Users can deploy it on their own machine, or in the cloud to ramp up its skills.