The Verge: Google Photos now lets you search for text in pictures you’ve taken. “Google made a subtle announcement today on Twitter: it’s in the process of rolling out new AI features for its Lens platform that will let you search your Google Photos library for text that appears within photos and screenshots. Then, you’ll then be able to easily copy and paste that text into a note, document, or form.”
Online Journalism Blog: When you get data in sentences: how to use a spreadsheet to extract numbers from phrases. “We needed to be able to take a collection of words such as ’11 years and 5 months’ imprisonment’ and convert that into something that could be used in spreadsheet calculations (specifically, comparing the lengths of time represented by two different phrases). It’s a problem you come across every so often as a journalist — especially with FOI requests — so in this post — taken from the book Finding Stories in Spreadsheets — I’ll explain how to do that.”
Engadget: Amazon’s Textract AI can read millions of pages in a few hours. “Amazon has launched a new offering called Textract for its Web Services customers, and it’s like optical character recognition on steroids. It more than just extracts text from documents like its name implies — Amazon says it can actually identify different document formats and their contents so it can process them properly.” Apparently not available all over the US yet.
Hongkiat: How to Extract Text from Images Using Command Line . “It’s easy enough to read an image and pull the text yourself. But dynamically pulling text from a photo is a bit tougher, and thankfully, imgclip offers a fairly simple solution.”
EurekAlert: OCR: Modern tool for old texts. “With OCR4all, the JMU [Julius-Maximilians-Universität Würzburg] research team is making a new tool available to the scientific community. It converts digitized historical prints with an error rate of less than one percent into computer-readable texts. And it offers a graphical user interface that requires no IT expertise. With previous tools of this kind, user-friendliness was not always given as the users mostly had to work with programming commands.”
ZDNet: Microsoft starts rolling out ability to turn photos of table data into Excel spreadsheets. “Microsoft has started making available its ‘Insert Data from Picture’ feature that allows users to take pictures on their phones of table data and automatically turn it into an Excel spreadsheet. Microsoft announced this feature at its Ignite conference last September.”
VentureBeat: AI extracts speech bubbles from comic strips. “Segmentation — partitioning an image or scan into multiple segments, or sets of pixels — is a task at which artificial intelligence (AI) excels. Case in point: Researchers at Google parent company Alphabet’s DeepMind recently revealed in an academic paper that they’d developed a system capable of segmenting CT scans with ‘near-human performance.’ Now, scientists at the University of Potsdam in Germany have developed an AI segmentation tool for a slightly more cartoony medium: comics.”