Georgia Tech students explore color recognition in artworks through an innovative fusion of APIs and machine learning. The research utilizes the Art Institute of Chicago's API for metadata acquisition, combined with a color clustering algorithm, allowing for a detailed statistical analysis of color usage in
Ebonique Boyd (product lead) examimes the implications of the Fear of Missing Out (FOMO) in app design, arguing for a more user-centric approach that prioritizes satisfaction and wellbeing. We delve into the concerning rise of anxiety among young adults, drawing links to certain design practices.
This team from Georgia Tech discuss the process of data cleaning and analysis in the context of studying color patterns in artworks. They used a dataset from the Art Institute of Chicago, consisting of 122,435 artworks, for this purpose. The data was cleaned to extract
This blog post titled "Giving Color Vision to a Machine" by Global Data Artists delves into the intricate process of training a machine to recognize and categorize similar colors within different images. The authors detail their approach of employing KMeans clustering on image data, confronting
This article explores the use of clustering algorithms and art museum APIs to extract dominant color palettes from artworks, with a focus on the collection of the Art Institute of Chicago. The authors demonstrate how to programmatically access image and metadata, extract color statistics, and
The article discusses a project to analyze patterns in the use of colors in paintings by using a 3D K-Means clustering algorithm to extract the dominant colors in images and their associated metadata, and then using this data to perform time series and spatial regression.