Add to Favourites
To login click here
Adobe is seeking to patent a system for “diversity auditing” using computer vision. The system uses facial detection and image classification to break down photos of employees and slot them into categories based on certain physical traits and characteristics. It then calculates a “diversity score” for the set of images using machine learning by comparing the classified images to a comparison population. Potential problems exist with a system like this, such as measuring diversity from photos being a difficult task and not accounting for people of multiple races or gender-nonconforming individuals.