Google program can automatically caption photos

A neural network-based system scores above average in writing natural captions

“Two pizzas sitting on top of a stove top oven," is how a Google program described this image.

“Two pizzas sitting on top of a stove top oven," is how a Google program described this image.

Next time you're stumped when trying to write a photo caption, try Google.

The search giant has developed a machine-learning system that can automatically and accurately write captions for photos, according to a Google Research Blog post.

The innovation could make it easier to search for images on Google, help visually impaired people understand image content and provide alternative text for images when Internet connections are slow.

In a paper posted on arXiv, Google researchers Oriol Vinyals, Alexander Toshev, Samy Bengio and Dumitru Erhan described how they developed a captioning system called Neural Image Caption (NIC).

NIC is based on techniques from the field of computer vision, which allows machines to see the world, and natural language processing, which tries to make human language meaningful to computers.

The researchers used two different kinds of artificial neural networks, which are biologically inspired computer models. One of the networks encoded the image into a compact representation, while the other network generated a sentence to describe it.

The researchers' goal was to train the system to produce natural-sounding captions based on the objects it recognizes in the images.

NIC produced accurate results such as "A group of people shopping at an outdoor market" for a photo of a market, but also turned out a number of captions with minor mistakes, such as an image of three dogs that it captioned as two dogs, as well as major errors, including a picture of a roadside sign that it described as a refrigerator.

Still, the NIC model scored 59 on a particular dataset in which the state of the art is 25 and higher scores are better, according to the researchers, who added that humans score around 69. The performance was evaluated using a ranking algorithm that compares the quality of text generated by a machine with that generated by a human.

"It is clear from these experiments that, as the size of the available datasets for image description increases, so will the performance of approaches like NIC," the researchers wrote.

Join the newsletter!

Or

Sign up to gain exclusive access to email subscriptions, event invitations, competitions, giveaways, and much more.

Membership is free, and your security and privacy remain protected. View our privacy policy before signing up.

Error: Please check your email address.

Tags internetGooglesearch engines

Keep up with the latest tech news, reviews and previews by subscribing to the Good Gear Guide newsletter.

Tim Hornyak

IDG News Service
Show Comments

Most Popular Reviews

Latest Articles

Resources

PCW Evaluation Team

Tom Pope

Dynabook Portégé X30L-G

Ultimately this laptop has achieved everything I would hope for in a laptop for work, while fitting that into a form factor and weight that is remarkable.

Tom Sellers

MSI P65

This smart laptop was enjoyable to use and great to work on – creating content was super simple.

Lolita Wang

MSI GT76

It really doesn’t get more “gaming laptop” than this.

Jack Jeffries

MSI GS75

As the Maserati or BMW of laptops, it would fit perfectly in the hands of a professional needing firepower under the hood, sophistication and class on the surface, and gaming prowess (sports mode if you will) in between.

Taylor Carr

MSI PS63

The MSI PS63 is an amazing laptop and I would definitely consider buying one in the future.

Christopher Low

Brother RJ-4230B

This small mobile printer is exactly what I need for invoicing and other jobs such as sending fellow tradesman details or step-by-step instructions that I can easily print off from my phone or the Web.

Featured Content

Don’t have an account? Sign up here

Don't have an account? Sign up now

Forgot password?