Skip to content

Loretta C. Duckworth Scholars Studio

⠀

Menu
  • Scholars Studio Blog
    • Digital Methods
      • coding
      • critical making
      • data visualization
      • digital pedagogy
      • immersive technology (AR/VR)
      • mapping
      • textual analysis
      • web scraping
    • Disciplinary Fields
      • Anthropology
      • Archaeology
      • Architecture
      • Art History
      • Business
      • Computer Science
      • Critical Digital Studies
      • Cultural Studies
      • Dance
      • Economics
      • Education
      • Environmental Studies
      • Film Studies
      • Gaming Studies
      • Geography
      • History
      • Information Science
      • Linguistics
      • Literary Studies
      • Marketing
      • Media and Communication Studies
      • Music Studies
      • Political Science
      • Psychology
      • Public Health
      • Sculpture
      • Sociology
      • Urban Studies
      • Visual Art
  • Current Staff
  • Current Fellows
    • Faculty Fellowships
    • Graduate Extern Program
  • About
  • Newsletter
Menu

Coloring Your Data- The Art of Digital Video and Image Visualization (Part II)

Posted on February 2, 2016January 24, 2023 by Ping Feng

By Ping Feng

In last section, we just displayed some digital video visualization projects that highlight color and editing pattern display. In this section, I will introduce some visualization projects that focus on displaying the color hue patterns or brightness patterns for large set of digital images.

Softwarestudies.com has created a very useful tool- ImagePlot to help us visualize large set of digital images by inputing the metadata and original graphic images. The tool allows us to choose two dimensions of the image data to display, e.g. time longitude in x axis and brightness in y axis. Below is a sample display of a collection of Van Gogh’s paintings with the x axis showing the year and time information and y axis presenting the brightness information.  We can easily observe the trend that when it comes to the later stage of his life, Van Gogh’s painting tends to be lighter. Thus, it allows us an easier way to observe the pattern of large sets of images, discover insights and tell the story behind it by visualizing art history so that humanistic analysis can be undertaken at a broader scale.

van_gogh_data.txt - Year_Month vs Brightness_Median

Netflix has utilized color analysis in digital video/ image materials for consumer insight and business intelligence:

color picturecolor

Figure1: Cover of House of Cards Versus Cover of Macbeth (2010 version)

netflix_color two contrastcolor contrast

Figure2: Detailed Color Comparison of House of Cards and Macbeth 

Figure3: Detailed Color Comparison of hemlock Grove, House of Cards, and Arrested Development 

Source: Netflix Technology Blog (techblog, netflix.com), Big Data Lessons From Netflix(Wired)

As we can see in figure1 that the covers of House of Card and Macbeth are quite similar to each other at the first glance: both displays older white men with blood on their hands agains primarily black or grey backgrounds. And this can be further confirmed by looking at figure2 which illustrates the detailed color break down. The comparison demonstrates that the covers of the two shows are quite similar, though differences do exist. By the same token, figure3 demonstrates the contrast of color distribution of the covers among three different shows.  Below video also shows a surprisingly color hue consistency among various shot in House of Cards: 

Source: How the Colors Blue and Yellow Help House of Card Become One of the Most Beautifully Shot Series Ever

Then what’s the value for Netflix to invest efforts in doing so? Why is it necessary to quantify and compare those detailed color differences? The potential value will be tremendous if we take one step further to look at it. First, it will be easier for Netflix to see if this will have discernible impact on subscriber viewing habits, recommendations, ratings, and the like and therefore acquire informed decision-making in business. In addition, as one Netflix leader has confessed at a Hadoop summit, analyzing colors will allow company to measure the distance between customers and develop a database and algorithm to determine the average color of tiles for each customer in a 216-degree vector over the last N days, which will further inform them in precise-targeting.

Leave a Reply

You must be logged in to post a comment.

Recent Posts

  • Web Scraping Wikipedia to Analyze XBOX Game Development Companies by Nationality January 4, 2023
  • Critical Elements for Making Games December 22, 2022
  • Cities as Havens for Bees: Using Remote Sensing to Visualize Urban Bee Habitat December 21, 2022

Tags

3D modeling 3D printing 360 video arduino augmented reality authorship attribution coding corpus building critical making Cultural Heritage data cleaning data visualization digital art history Digital Preservation digital reconstruction digital scholarship film editing games GIS linked open data machine learning makerspace mapping network analysis oculus rift omeka OpenRefine Photogrammetry physical computing Python QGIS R SketchUp stylometry text analysis text mining textual analysis top news twitter video analysis virtual reality visual analysis voyant web scraping YouTube

Archives

©2023 Loretta C. Duckworth Scholars Studio | Design: Newspaperly WordPress Theme