Large-Scale Twitter Food Photo Mining and Its Applications

Many people are posting photos as well as short messages to Twitter every minutes from everywhere on the earth. By monitoring the Twitter stream, we can obtain various kinds of photos with texts which help understand the current state of the world visually. Since 2011, we have been continuously collecting photos from the Twitter stream for about eight years. We are collecting food photos as well as generic geotagged photos, since we are intensively working on multimedia processing on foods. In this paper, we focus mainly on Twitter food photos. Because foods are one of the most popular contents of Twitter photos, we can collect a large number of food images from Twitter. In fact, we have collected more than two million food photos so far. In this paper, we present the analysis on the food photos collected from the Twitter stream. In addition, we describe some applications using Twitter photos including world food photo analysis and food photo translation/generation.