New application features accurate and easy-to-use facial recognition technology.

Exadel, a global provider of digital software engineering solutions and services, announced the release of CompreFace, an open-source facial recognition application. CompreFace can be integrated as a standalone service or deployed via the cloud. Its convenient API offers state-of-the-art facial recognition.

To get started with Compreface, visit: (https://github.com/exadel-inc/CompreFace#overview)

“Facial recognition technology is being rapidly adopted across a variety of industries, including retail, travel, and hospitality. However, not everyone has the machine learning experience necessary to develop and deploy facial recognition efficiently and effectively,” said Lev Shur, president of Exadel Solutions. “Exadel designed CompreFace as a facial recognition solution that can be leveraged no matter what level of machine learning knowledge the end-user has. And since it is an open-source solution, users can trust the quality and security of the app.”

Read More : How Disinformation Affects CISOs

CompreFace features include:

• Open-source code and available fully on-premise. This increases data security and ensures the quality of the program. CompreFace can also be deployed on the cloud, if needed.
• Can be set up and used without machine learning knowledge. Building in-house face recognition technology is complex and time-consuming. CompreFace allows anyone to easily integrate additional security measures without necessarily hiring outside help.
• Uses one of the most popular face recognition methods with high accuracy. CompreFace uses deep neural networks — a highly-regarded face recognition method. CompreFace has demonstrated accuracy even when there is only one example of a face.
• UI panel with roles for access control. CompreFace’s “roles system” controls which users can access the Face Collection. Additionally, each user can create several Face Collections based on different subsets of people.
• Fast start with one docker command.