Today, Google announced the beta release of its Google Cloud Vision API. The API was designed to empower applications to both see and understand images submitted to the API. With powerful features such as label/entity detection, optical character recognition, safe search detection, facial detection, landmark detection, and logo detection; the Cloud Vision API gives applications unprecedented ability to comprehend the situation within an image.
With the new API, Google enters a rapidly developing market where both startups and major enterprises are producing cutting edge technology. From Microsoft, with its Project Oxford, to niche startups like Cognitec and Lambda Labs; image analysis is proving to be an attractive space as it appeals across industries from marketing to security. Google has taken a unique approach in that it offers various image analysis techniques from a single platform. Where many companies focus on a single feature (e.g. facial recognition, OCR, labeling, etc.), Google will go to market with a single platform for all image analysis techniques and features.
Google originally launched a Cloud Vision API preview at the end of last year. Since then, developer uptake and feedback exploded. Accordingly, Google has now opened the beta to the broader community with full documentation, sample apps, Google Cloud storage, and pricing announcements. The pricing announced becomes effective on March 1, 2016.
The API provides a robust set of features that analyze images. API features include: label detection (detects a broad set of categories within an image; such as mode of transportation and animals), text detection through OCR, explicit content detection, logo detection, landmark detection (popular natural and man made structures), image attributes (dominant color, etc.), and face detection (facial attributes, emotional state, etc.). Apps can request one or more types per image.
During the beta, the user quota is 20 million images per month. The API is not currently designed for real-time, mission critical applications. Check out Google's sample apps to get the creative juices flowing, and the API docs to learn more. Per usual, Google encourages beta testers to provide feedback