Twitter has used machine learning to improve its automatic image cropping for photos across the platform.
Important focus points in an image were previously identified using facial recognition and defaulting to a centre crop if no face was detected.
Twitter admitted this prediction method was ineffective, and has now turned to a prediction model based on saliency.
Using data recorded in academic studies, Twitter’s neural networks detect the focal point of an image, resulting in better automatic cropping.
Join the conversation Autoload comments
Comments section policy: MyBroadband has a new article comments policy which aims to encourage constructive discussions. To get your comments published, make sure it is civil and adds value to the discussion.