Recently Google has announced BETA release of it’s Google Cloud Vision API which can be a great service for developers. The API provides developers access to high value service that let’s anyone to develop and build up an idea. Anyone can make use of it and submit images to understand the content in them and detect objects such as car, dish, bird, read text or identify product logos and more.
The Cloud Vision API will provide developers access to its API (BETA) with location of images stored in Google Cloud Storage, alongside with existing support for embedding an image as part of the API request.
They are also announcing prices for the Cloud Vision API and have added more capabilities to identify the dominant color of an image. For instance, now you can apply Label Detection in about $2 per 1,000 images or Optical Character Recognition (OCR) for $0.60 for 1,000 images. The new effective prices will start from March 1st.
What Google Cloud Vision API actually is? – It provides powerful image analysis by helping developers to understand the content of an image by encapsulating powerful machine learning models in an easy to use REST API.
It classifies images into thousands of categories such as Boat, Tiger and Eiffel Tower etc, detects individual objects and faces within images, finds and reads printed words contained within images.
Allows you to build metadata on your image catalog, moderate offensive content, or enable new marketing scenarios through image sentiment analysis. You can analyze images uploaded in the request or integrate with your image storage on Google Cloud Storage. During Beta, Vision API is not intended for real time usage on mission critical applications.
Scenarios supported by Cloud Vision API BETA release:
- Insights from your images: Cloud Vision API detects wide range of objects inside images including birds, flowers and landmarks. Powered by the technologies that work for Google Photos.
- Inappropriate content detection: This is one great feature, powered by Google SafeSearch. The API moderates content by detecting various types of inappropriate content.
- Image sentiment analysis: It can also analyze emotional attributes such as anger, joy and sorrow of people in images. This is not all, it can also detect logo of popular products.
- Text extraction: Optical Character Recognition (OCR) allows you to detect text written in your images. It also identifies language of the text automatically.
So these are some of the great features that developers are now able to implement in their applications. There are many companies using the API and generating millions of requests for image annotations since the limited preview of Google Cloud Vision API was announced in early December.
During the beta timeframe of the API, developers will be provided a quota of 20 million images per month. The documentation can be accessed here, with examples and lessons explaining the usage of the API in Python and Java alongside with Android and iOS app samples.