The researchers at the Penn State University have developed software named Automatic Linguistic Indexing of Pictures Real-Time, commonly known as ALIPR that can identify the images and accordingly gives tags to them.

During the test a photo of polo match yielded results like “sport”, “people”, “horse”, “polo”.

Currently the system has a vocabulary of 322 words to describe what it sees in the image.

The analysis takes about 1.4 seconds per image and has a 98% success rate in identifying at least one correct tag.

Via: wincustomize