This repository documents the workflow and R code that can be used to classify a large number of images into discrete categories, based on their content. It provides supplementary information to the following paper:
Song, X.P., Richards, D.R., Tan, P.Y. (2020). Using social media user attributes to understand human–environment interactions at urban parks. Scientific Reports 10, 808. https://doi.org/10.1038/s41598-020-57864-4
The HTML document Photo_classification.html demonstrates how to generate photograph keywords using the Google Cloud Vision API, and classify photographs based on similarities between their keywords. The file is viewable at this link.
The same file is viewable partially-rendered in intermediate markdown (Photo_classification.md), or in this blog post.
Photograph metadata in the 'data' folder is used as an example.