OCR Stories June 1, 2016

Update: In a blog post, Google details new features currently available in English and rolling out soon to other languages. Now on Tap now officially works in the camera app and for images. For instance, users can open the camera app and initiate Now on Tap to identify landmarks. It can also be used in apps like Pinterest to identify artwork.

Rolled out last night to all users, Now on Tap has a new interface and the ability to manually select text from anything in a screenshot to perform a search. Due to a number of factors, Now on Tap has yet to become a hit feature and today’s update is a meaningful change to the product.

expand full story

OCR Stories March 8, 2016

Latest Google app beta adds OCR image recognition to Now on Tap

For all the features the Google app has added, it still does not have any image recognition capabilities. Google Goggles from 2010 could recognize book covers, landmarks, and even solve Sudoku, but was ultimately discontinued due to a lack of use. However, Now on Tap has gained some of those features in a recent update.

OCR Stories February 18, 2016

Google’s image scanning Cloud Vision API gets official pricing as it enters open beta

If you’ve searched for objects or landmarks in Google Photos, you have already used Google’s Cloud Vision API without knowing it. Today, the Mountain View company announced that it is now opening up the API to more developers as it enters beta. Launched in limited preview last December, Google has also announced pricing for the service.

OCR Stories May 6, 2015

Google Drive’s OCR feature now lets you edit scanned docs in 200+ languages

 

Google has long had Optical Character Recognition features in Google Drive, allowing scanned paper document uploaded to Drive to be indexed and edited. Now, Google just recently expanded the feature to more than 200 languages and 25 writing styles.

To make this possible, engineering teams across Google pursued an approach to OCR focused on broad language coverage, with a goal of designing an architecture that could potentially work with all existing languages and writing systems. We do this in part by using Hidden Markov Models (HMMs) to make sense of the input as a whole sequence, rather than first trying to break it apart into pieces. This is similar to how modern speech recognition systems recognize audio input…

Once you scan a document and upload it to Drive, you just need to right-click on it and select ‘Open with’ -> ‘Google Docs’.

Google adds that you don’t even need to set your language preference, Drive will automatically detect it when uploading a document.

You can access the OCR features both on the web and through the Google Drive app for Android.

Powered by WordPress.com VIP