Our paper compares content, photo techniques and visual styles of 100,000 Instagram images shared in a number of global cities. We use computer vision to detect 1000 types of content and 50 aesthetic features and then compare the images on these dimensions using three different methods.
Lev Manovich (The Graduate Center, CUNY), Miriam Redi (Bell Labs), Damon Crockett (UCSD), and Simon Osindero (Flickr).
Download ArticleWhat Makes Photo Cultures Different?, ACM, October 2016.
Our paper compares content, photo techniques and visual styles of Instagram images shared in a number of global cities. Using deep learning, we detect 1000 types of content in the dataset of 100,000 images. We also extract 50 features that describe visual styles, photo techniques and aesthetic properties of these images. We propose and test a few different methods for comparing image samples shared in five cities these using content and visual features.
The first method uses a custom visualization technique and clustering. The second method uses supervised learning multi-class classification to quantify the differences between cities’ images. The third method compares the images along stereotypical/unique dimension.