The Cat Within – Google Image Recognition

Google can see cats

The unofficial star of the Internet is the cat. As a running joke concerning the ease by which time can be wasted online, cat videos and the grumpy cat are recurring stars. Google has now reinjected legitimacy into this cultural meme by using visuals of cats as a flagship for its new image recognition technology which uses artificial-intelligence software to interpret what is going on in a photograph, and then produce a descriptive caption.

Although such an activity seems relatively easy for a human, the ability to separate out the shapes and colors in a picture and place them into context requires an enormous amount of processing power, not only to determine what the objects represent in a picture, but the circumstances surrounding why they are there at all.

The Cat Connection

The cat connection comes from one of the more recent Google projects, in which, in 2012, a joint Google/Stanford team showed millions of images from YouTube videos to a computer that then taught itself how to recognize cats in the images.

According to Google’s own blog, the model for image recognition comes from adapting language processing applications, such as those that would convert a French phrase into a vector representation, which could then be translated into German. Vector recognition is described in a separate Google blog as follows: “[The computer] understands that Paris and France are related the same way Berlin and Germany are (capital and country), and not the same way Madrid and Italy are. [From this] it can learn the concept of capital cities, just by reading lots of news articles — with no human supervision.” The adaptation of vector representation is then blended with image processing software to essentially determine what is a cat and also what is not a cat.

Google concedes that the process is as yet far from perfect. Many of the photographs are misinterpreted, from mildly to wildly as the computers struggle to connect what they see with what actually occurs in the human world.

However as the image of their November 17 2014 post shows, “Two pizzas sitting on top of a stove top oven” is a fair assessment of what is going on in this image.

The potential for image recognition of this sort is limitless. Some immediate uses range from describing images to the visually impaired to faster and more accurate placement on Google Maps by reading house numbers.

By Steve Prentice

Isc2

Episode 2: Coronavirus Phishing Emails and Work-from-Home Meetings

Coronavirus Phishing Emails What to watch out for as scammers exploit pandemic panic, and tips on how to attend meetings while working from home. Working ...
Sangeeta Chhabra

Why ‘Cloud’ Should Be A Skill In This Age of Automation

The Age of Automation It is astonishing how the world around us is changing rapidly. More and more companies are now planning their move to ...
Bittitan

Episode 6: Cloud Migration: Why It’s More Important Than Ever

The Importance of Cloud Migration Moving fully to the cloud is still a concern for many companies, but with millions of employees working from home, ...
Hillary T

The Current Wave of Smart Home Technology

The Future of Smart Home Technology Some say the vision of smart homes kicked off with the invention of household machines in the early part ...
Aruna Headshot

2019 Predictions for Innovating, Transforming and Enabling Workplace Transformation

My Predictions for 2019 As we think of the top Collaboration trends for the coming year, we should start by taking a look back at ...
Bill Talbot

How IT Operations Can Survive and Thrive in a Multi-cloud World

IT Operations Can Thrive in a Multi-cloud World IT operations teams are contending with the reality that growing volumes of workloads are running across multiple ...
The Manuscript.png