Artificial Intelligence Vision

Deep Learning-powered image recognition is now performing better than human vision on many tasks.

The human sense of vision is unbelievably advanced. Within fractions of seconds, we can identify objects within our field of view, without thought or hesitation. But not only can we name objects we are looking at, we can also perceive their depth, perfectly distinguish their contours, and separate the objects from their backgrounds. Somehow our eyes take in raw voxels of color data, but our brain transforms that information into more meaningful primitives – lines, curves, and shapes – that might indicate, for example, that we’re looking at a can of Coke.

Below is the list of examples created with Google Cloud and Pervasive Technologies for cases posed by our customers.

Genre and age detection

• Given images, as static files or as a video streams, we detect the genre of the individual and the age range.

Image Classification and localisation

• Given images, as static files or as a video streams, we detect classes of objects contained.

Object counting per class

• After detecting classes of objects in images, we can count them

Product Quality Control

• Computer vision algorithms based on machine learning can learn from a set of samples to distinguish the “good” samples from the flawed ones.

Visual Similarity Search

• There’s one type of search query that’s very explicit, specific, and interesting – a visual similarity search, after you snap something in the real world. Visual search, which finds visually similar products based on an sample image can provide a collection of very relevant results.