The Verge: Google Translate can now visually translate 13 more languages. “Starting this week, the Google Translate app will be capable of visually translating 13 new languages by using the camera on your smartphone, according to a report from VentureBeat. In 2015, Google added the visual translation feature to the Translate app with the support of 27 different languages. It allows users to translate dinner menus and signs in real time, making communicating abroad much easier. ”
TechCrunch: Dropbox finally adds automatic OCR for all your PDFs and photos . “Enterprise Dropbox users have a useful new feature that some would say is long overdue for the cloud storage company: optical character recognition that automatically transcribes all their images and PDFs. No more rummaging around in your saved photos for a receipt or opening dozens of mysteriously named documents to find the right one. Just search and ye shall find.”
TechCrunch: Google Street View rival Mapillary collaborates with Amazon to read text in its 350M image database . “Mapillary, the Swedish startup that wants to take on Google and others in mapping the world by way of a crowdsourced database of street-level imagery, is taking an interesting step in the development of its platform. The company is now working with Amazon, and specifically its Rekognition API, to detect and read text in Mapillary’s database of 350 million images.”
MakeUseOf: How to Cleanly Extract Text From Images on Your Computer Screen. “If you have any experience with computers, you’ve probably heard of Optical Character Recognition (OCR). This important procedure takes images that have text in them and extracts that text into an editable form. For instance, Google uses OCR to scan old books and make them available digitally through Google Books. But OCR can be useful to you as a home user too. Let’s take a quick look at an app that makes it easy.”
Abundant Genealogy: Newspaper Clippings – Using Reverse Search to Cite Sources and Save Your Sanity. “A well-meaning relative sends you a packet of newspaper clippings about your ancestors. Or you receive several obituaries pasted to 3×5 inch index cards. Or you are given a scrapbook created in the 1920s or 1930s with a variety of news articles clipped from newspapers and magazines. Of course, when clipped there is no date, no newspaper masthead or header with the name, volume number, page number etc. Your relative (or someone) may have handwritten the date or other information along the margins, but rarely do they include everything you need as a researcher. So how do you track down the original source and cite it properly?” nicely done!
British Library: 8th Century Arabic science meets today’s computer science. “Supporting the use of Asian & African Collections in digital scholarship means shining a light on this stark divide and seeking ways to close the gap. In this spirit, we are excited to announce the ICFHR2018 Competition on Recognition of Historical Arabic Scientific Manuscripts.”
Digital Inspiration: Search your Handwritten Notes with Gmail OCR. “Gmail text search has always been very capable but some might not know that Gmail, like Evernote, also performs OCR on images contained in email messages. When you perform searches inside Gmail or Google Inbox, the results always contain matching images that contain the search keywords. I tried Gmail OCR search against different types of images and the results were fairly good. Text recognition in Gmail works for both image attachments as well as inline embedded images.”