Making computers see with Goggles and translate pictures into words

Relaxnews
Friday 07 May 2010 11:45 EDT
Comments

Your support helps us to tell the story

From reproductive rights to climate change to Big Tech, The Independent is on the ground when the story is developing. Whether it's investigating the financials of Elon Musk's pro-Trump PAC or producing our latest documentary, 'The A Word', which shines a light on the American women fighting for reproductive rights, we know how important it is to parse out the facts from the messaging.

At such a critical moment in US history, we need reporters on the ground. Your donation allows us to keep sending journalists to speak to both sides of the story.

The Independent is trusted by Americans across the entire political spectrum. And unlike many other quality news outlets, we choose not to lock Americans out of our reporting and analysis with paywalls. We believe quality journalism should be available to everyone, paid for by those who can afford it.

Your support makes all the difference.

Google has been busy teaching computers to understand how to translate the text found in pictures into new languages - a very helpful tool for people heading overseas and wanting to know what they are ordering from a foreign-language menu.

In February Google showed off a prototype version of their "Google Goggles" translation software - a mobile application that uses OCR (Optical Character Recognition) to translate text-based images from one language to another in real time.

In February Google Goggles was only able to recognize German text, but the May 6th update enables users to take pictures of English, French, Italian, German and Spanish text found on the signs, menus and documents around them. Once the text within the photo has been captured on a mobile device, it can be almost instantly translated into many other languages.

"In addition to translation, Goggles v1.1 features improved barcode recognition, a larger corpus of artwork, recognition of many more products and logos, an improved user interface, and the ability to initiate visual searches using images in your phone's photo gallery," said Google in a May 6 update on their Mobile Blog.

To use Google Goggles, users point their phone at the word or phrase they wish to have translated. Using the "region of interest button", users fine-tune their onscreen selection to a smaller area and then press the shutter button. If the text is recognised the application will give you the option to translate the text into another language.

Google confident that Google Goggle's language recognition capabilities will be expanded to other Latin-based languages in the near future and there are plans to expand their service to non-Latin languages such as Chinese, Hindi and Arabic too.

Software developers have been working on programs that can instantly recognise text in images for years, however, most solutions have proved to be expensive or fairly inaccurate at recognising and translating a wide range of languages and texts.

Other mobile-based OCR projects currently on the market include DIOTEK's MobiReader iPhone application, Cybercom's Nokia N900-based Photo Translation app, and a large range of mobile applications developed by Abby Mobile.

The update for Google Goggles is available for mobile devices running Android 1.6 and higher. Users can download Google Goggles from the Android Market for free.

http://googlemobile.blogspot.com/2010/05/translate-real-world-with-google.html

Join our commenting forum

Join thought-provoking conversations, follow other Independent readers and see their replies

Comments

Thank you for registering

Please refresh the page or navigate to another page on the site to be automatically logged inPlease refresh your browser to be logged in