Google is placing its Cloud Vision API into open beta.
That's probably a lot more interesting to developers than everday Google users. But Google's move now gives many more people another way to build image recognition into apps and devices—which could ultimately allow something like your set-top box to identify that you are actually you, and respond with movie recommendations based on what your facial gestures are suggesting your mood might be.
And there's more to Google's Cloud Vision API than novelty. Some companies have even been using the limited preview of the API to better police images that are uploaded to their services—a herculean task for any one person (or a team of people), depending on the popularity of the service.
"PhotoFy, a social photo editing and branding app, moderates over 150,000 photos a day created by a wide audience. Before the Cloud Vision API was available, CTO Chris Keenan said that protecting these branded photos from abuse was almost impossible. With the Cloud Vision API, PhotoFy can flag potentially violent and adult content on user created photos in line with their abuse policies," reads Google's blog post.
During its beta period, developers will be given a quota of 20 million images per month they're allowed to run through the Cloud Vision API. They can either embed images as part of an API request or they can use the API to analyze images that already exist in Google Cloud Storage. The API itself can find various items in images, and will even suggest landmarks if they're in the shot. It can also predict moods based on facial patterns, identify text (and its language), and even figure out what the dominant color of a particular image happens to be.
As part of its announcement, Google is also sharing pricing details for using the API.
"For example, you can now apply Label Detection on an image for as little as $2 per 1,000 images or Optical Character Recognition (OCR) for $0.60 for 1,000 images. Pricing will be effective, starting March 1st," reads Google's post.
Source: pcmag.com
0 comments:
Post a Comment