When Google released the Google Play Services v 9.2 update, it marked the triumphant return of something that many probably believe should never have disappeared in the first place. It was not even a year ago (August of 2015) that Google announced an application called Android Mobile Vision, an API which would allow developers to detect faces in images and video. This, of course, is similar to the way that tagging works in Facebook.
Well, not long after it was announced, the service disappeared thanks to a serious bugs that needed immediate address. During that time the service would inform developers to avoid adding any new features until they managed to fix the issue. Apparently, that time has come.
The good news is that it is back and the better news is that it is better than it was when it left. That much is to be expected, of course. It is also to be expected that the new API also comes with a text application that lets developers access yet more optical character recognition (OCR). Apparently this improves Google’s system in the realm of not only facial recognition but also the barcode-reading functionality of Android apps.
Google’s Text OCR technology can, at present, recognize any Latin-based language. This covers, of course, most European languages to include English, German, and French, and even Turkish. The API allows a device to detect text in real time, just like facial recognition and barcode readers. You could go so far as to say that the Mobile Vision OCR Text application works like a combination of facial recognition software and Google Translate.
Google’s OCR breaks down text into smaller pieces like paragraphs or lines or just a word and even just into text data itself.
Upon the release, too, Google has also provided a number of use-cases for the technology. The tech giant says that developers can use it to organize photos that have text in the image or to automate data entry for things like credit cards, receipts, or business cards: you know, things that are mostly text-based.
Moreso, though, the update could also be useful for the embedding of translate features through Google’s Cloud Translate API and to catalog and keep track of objects. On the other hand, though—and in true open-source fashion—developers could use the API to enable accessibility features via Android’s powerful TextToSpeech engine.