Google has made a breakthrough in image recognition software that can very accurately detail the happenings within an image. It can analyze a given image and create a human-like description of what it sees.
This new technology will be used for Google’s image search features, as well as other purposes such as helping blind users get a better idea of what lies within a picture.
The software functions through use of two neural networks developed by Google scientists (Oriol Vinyals, Alexander Toshev, Samy Bengio and Dumitru Erhan), and operates similar to the human brain.
Uses for such technology can be endless, and it will be exciting to see what they do with it in the near future.
You can read more about it at Google’s Research Blog.
