Darrell Etherington, tech crunch, 2014, Amazon Puts image Recognition Into Its Main IOS App, here. So take a picture of a book cover with your phone then Amazon will return the ISBN of the physical book. This code is on my iPhone for the last year or two. I use it and it works. All this “showroom” prose misses the boat. Assume all digital e-books are free, on average. Certainly with any given physical book, using this code, /lib can find the corresponding e-book once it knows the ISBN (e.g., the book goes directly to your /lib library’s flow shelves).
What you really want is a code that reads movies recorded from your phone of shelves of books. You want the vectorized version of the Amazon code. This must be doable at this point. The code reads the physical book spines and returns a list of ISBNs. I do not care how fast the code is .. let it run over night if need be to get the ISBNs. Once you have the ISBNs, the corresponding e-books appear in your /lib flow shelves. Applications – You go to libraries, private homes, book stores, offices … if you get a movie image of the physical book, run the code, get the ISBNs – it/they shows up in your digital library, sort out the copyright issues. Keep /lib as open software and the individual users can sort out the copyright issues, if there are any in the limit.
People already use their mobile devices for comparative shopping when paying visits to brick-and-mortar retailers – but it’s about to get a lot worse. Amazon has integrated shopping-by-camera functionality into its main iOS application, which is even easier than the previous barcode scanning feature it used to let shoppers compare prices.
The image recognition feature isn’t new: Amazon previously released a standalone app called “Flow” run by its subsidiary A9 (the search and advertising wing of the e-commerce giant), and the new feature within the main app is called “Flow,” too. The standalone app was launched a little over two years ago, so Amazon clearly wanted to make sure the image recognition tech was fully baked before introducing it to the wider user pool of its main iOS application.
Flow’s introduction (and its eventual rollout on Android, too) was preceded by Amazon A9’s acquisition of SnapTell, a startup whose main purpose was to develop visual product search. With SnapTell, you could take a picture of certain specific items (CD, DVD, book or video game covers to be exact) and get price and ratings from not only Amazon, but also Google, eBay and more.
The in-app Flow feature in Amazon’s iOS title is much more flexible – it works by identifying not only media package covers, but also logos, artwork and other unique visual features – and can cover a much broader range of packaged items. You still can’t take a picture of, say, a pair of headphones you have lying around the house out of box, but for showrooming purposes (its main use case) that shouldn’t matter all that much.
The ability to scan barcodes made it much easier for people to comparison shop, but it’s still a degree of complexity that makes it not all that convenient, since barcodes are sometimes difficult to find, and shoppers might not always know where to look for them, or want to bother. With straightforward package trait identification, it’s a simple matter of point-and-shoot, without even having to take an item down from its rack or shelf.
Amazon Rekognition, AWS, here.
Amazon Rekognition makes it easy to add image and video analysis to your applications. You just provide an image or video to the Rekognition API, and the service can identify the objects, people, text, scenes, and activities, as well as detect any inappropriate content. Amazon Rekognition also provides highly accurate facial analysis and facial recognition on images and video that you provide. You can detect, analyze, and compare faces for a wide variety of user verification, people counting, and public safety use cases.
Amazon Rekognition is based on the same proven, highly scalable, deep learning technology developed by Amazon’s computer vision scientists to analyze billions of images and videos daily, and requires no machine learning expertise to use. Amazon Rekognition is a simple and easy to use API that can quickly analyze any image or video file stored in Amazon S3. Amazon Rekognition is always learning from new data, and we are continually adding new labels and facial recognition features to the service.
Jack Crosbie, Medium, Jan. 2019, In the Future, Senior Citizens will play Video Games all day, here.
Other studies have had complimentary results. In 2014, for instance, a study by education psychologists at the University of Florida found that the popular 3D-puzzle game Portal 2improved respondents’ scores at basic cognitive tests more than the heavily marketed “brain trainer” Lumosity. Not all games, however, have the same effect. West’s research indicates that the “action video game” players were encouraging “response learning strategies” that rely on a different portion of the brain called the caudate nucleus. Over-reliance on the caudate nucleus can be detrimental to the hippocampus, which supports spatial memory — the goal is a balance between the two. And many modern games, action or otherwise, often furnish players with a mini-map and guided waypoint markers, creating a spatial situation where “the game’s doing the cognitive work for you,” he said.