IBM announced in early 2016 that its artificial intelligence (AI) pro-computer Watson AI gained image recognition capabilities. From today you can try it yourself!
A site connected to IBM Watson lets you feed the computer your own photos to see what it thinks is in them. The Results they are impressive.
The demonstration visualς αναγνώρισης, σας επιτρέπει να δώσετε στον Watson μια διεύθυνση URL της εικόνας ή να ανεβάσετε μια photo. The results come a little later (a few seconds) and display what he thinks he "sees."
On the test page, there are already uploaded photos, but you can also upload your own as mentioned above. Watson's test with some random photos already on the site was pretty accurate. He could perceive what was a landscape, an animal, which animal, or where it was located background.
From the same page you can also train Watson by uploading photos and making a rough classification. This way he can find out what he "sees" in the specific classification. You will need to upload more than 50 photos to be able to say what he "sees".
Here we have to say that the lifelong learning of the supercomputer will not only be based on your own photos. The system crosses data with every new photo it does not contain at its base. So with time it will become smarter.
The demonstration technique is available as an open source project. So anyone interested can clone it and run it on their own system….
See the photo recognition page
https://visual-recognition-demo.mybluemix.net/