Google’s New Technology Has a Super Sharp Sense of Object Recognition
Recent technology advancement has opened the possibility of more sophisticated image recognition features. Even though in recent year various researchers have come up with significant discoveries, the automatic object recognition in images is still considered tricky. However, Google is all set to change that. In other word, the internet giant has just come up with very sophisticated detection system hat can easily spot lots of objects in a scene, even if they’re partly obscured.
“This effort was accomplished by using the DistBelief infrastructure, which makes it possible to train neural networks in a distributed manner and rapidly iterate. At the core of the approach is a radically redesigned convolutional network architecture. Its seemingly complex structure (typical incarnations of which consist of over 100 layers with a maximum depth of over 20 parameter layers), is based on two insights: the Hebbian principle and scale invariance.” the Google research blog reads.
The result of this groundbreaking technology is far deeper scanning system that can both identify more objects and make better guesses, and will be able to spot tons of mundane items around you.
This technological advances will enable even better image understanding and the progress can be directly transferred to Google products such as photo search, image search, YouTube, self-driving cars, and any place where it might be useful to understand depth, perception and imagery.