Speedy Neural Networks for Smart Auto-Cropping of Images

 

The ability to share photos directly on Twitter has existed since 2011 and is now an integral part of the Twitter experience. Today, millions of images are uploaded to Twitter every day. However, they can come in all sorts of shapes and sizes, which presents a challenge for rendering a consistent UI experience. The photos in your timeline are cropped to improve consistency and to allow you to see more Tweets at a glance. How do we decide what to crop, that is, which part of the image do we show you?

 

Twitter will have feature like Snapchat ?

twitter image feature

 

Previously, Twitter used face detection to focus the view on the most prominent face we could find. While this is not an unreasonable heuristic, the approach has obvious limitations since not all images contain faces. Additionally, our face detector often missed faces and sometimes mistakenly detected faces when there were none. If no faces were found, we would focus the view on the center of the image. This could lead to awkwardly cropped preview images.

 

The reported innovation could be part of Twitter’s continual effort to increase its user-base, and profitability. In October, Twitter announced that they had miscounted the number of users on their platform, in addition to reporting relatively flat growth. But the third quarter of 2017 showed that they were nearing profitability, and got back on track in terms of audience growth.

Since this new camera feature would come on the heels of the 280 character count expansion, it looks like Twitter is looking for more ways to enable their users to create dynamic content — a decided shift from the minimalist, text-only 140 character count capabilities of yore. Kinda makes you wish for the days when every app wasn’t trying to be everything at once. .