YouTube trains its thumbnailer to generate better images

Since a YouTube video's thumbnail could convince or deter viewers from hitting play, we're sure a lot of creators would love the website's new and improved automatic thumbnailer. According to the Google Research Blog's announcement post, the website analyzes videos you upload at one frame per second and scores each frame based on their quality. The generator will then display images that scored high enough during analysis. But, how exactly does YouTube's algorithm know how to score images? Apparently, by training it to recognize between good and bad photos.

YouTube's developers fed its deep neural network with examples: they used typically well-constructed custom thumbnails uploaded by creators to represent good/high-quality ones, while the bad/low-quality samples were just random screen captures. Based on the comparison images the YT team posted, the upgraded algorithm successfully learned from the process and can pinpoint HQ photos. Thankfully, the generator's now live, so you can try it out for yourself and see if that's really the case.

Image