Google Vision is a new API that enables users to identify the contents of an image using Google's Machine Learning technology.
If you've uploaded a photo to Google Image search lately, you may have notice it's got a lot smart Or if you've used Google Photos on your smartphone, it seems to know what's in each image.
You may have noticed "Best Guess for this image..." followed by the name of what's in the photo.
Upload a dog or cat to Google, and it can spot it. It does this by examing the photograph using machine learning technology.
Behind the technology is a powerful Google Cloud Vision API. This API is available to developers.
Because the Raspberry Pi can be quickly turned into a camera. With the help of the Pi Camera accessory. This tech enables you to create a simple all-in-one smart camera. You can photograph items and use machine learning to identify them.
Build a Google Cloud Vision Camera
Dexter Laboratories has created a neat tutorial video: Introduction to Google Vision and The Raspberry Pi Camera.
Over on Dexter Industries website, you'll find detailed information on the build. It uses the following equipment:
- Raspberry Pi
- Raspbian for Robots SD Card
- Power Supply
- Raspberry Pi Camera
- Google Cloud Account
According to Google's Cloud Vision page: "Google Cloud Vision API enables developers to understand the content of an image by encapsulating powerful machine learning models in an easy to use REST API. It quickly classifies images into thousands of categories (e.g., "sailboat", "lion", "Eiffel Tower"), detects individual objects and faces within images, and finds and reads printed words contained within images. You can build metadata on your image catalog, moderate offensive content, or enable new marketing scenarios through image sentiment analysis. Analyze images uploaded in the request or integrate with your image storage on Google Cloud Storage.
