Google makes a tool that can blur parts of videos available as open source

Google has made open source a machine learning tool that allows users to blur parts of a video or image. The tool can protect people’s identities, the company says.

The tool is called Magritte and is available via GitHub. The machine learning tool can detect objects in videos and images without the need for a powerful computer. If the tool recognizes an object that needs to be blurred, Magritte will do this automatically. Examples of objects are according to Google license plates and tattoos.

Google says that the code is mainly useful for video journalists who want to better safeguard the privacy of those involved. The tool could fade faster than if one had to do this manually, while still maintaining high accuracy, Google claims. Magritte would also be useful for developers and researchers who want to analyze data without being exposed to privacy-sensitive information.

The company says it has further improved its Fully Homomorphic Encryption Transpiler, a technique the company released a year ago. With fhe, developers can work with encrypted data without having access to privacy-sensitive data in that encrypted data. Google says it has improved that transpiler over the past year; the circuit size is now 50 percent smaller, making the transpiler work faster. According to Google, Fhe would be useful for, for example, financial service providers, healthcare and governments, where encrypted data must be used in a secure manner.