Image analysis and visualization techniques for digital humanities | instructor: Lev Manovich | course at UCSD, spring 2011

One million manga pages
Researchers from Software Studies Initiative exploring one million manga pages dataset on HIPerSpace supervisualization system at Calit2.

Keywords: digital humanities, Calit2, UCSD, NEH, HIPerSpace, visualization, cultural analytics,, software studies, Lev Manovich

Spring 2011 / Visual Arts Department / UCSD
tIme: Wednesday, 3:00-5:50pm
instructor: Lev Manovich
office hours: Tuesday 2-3pm @Cafe Roma, or by appointment

All readings for this class will be available online at no charge.

The class will use free publicly available software as well as software tools developed by Software Studies Initiative.

Course description:  

“The next big idea in language, history and the arts? Data.”
New York Time, November 16, 2010.

Cultural Analytics is the use of computational methods for the analysis of patterns in visual and interactive media.

Our core methodology combines digital image analysis and next generation visualization technologies being developed at Calit2 and UCSD. We also developed an alternative methodology to explore large visual data sets directly, without any quantitative analysis.

More information about cultural analytics
Examples of cultural analytics projects

In the first part of the class the students learn cultural analytics techniques and software tools. In the second part all students work collaboratively on a project to create dynamic animated visualizations of large visual data sets.

The data may include visual art, graphic design, photography, fashion/street styles, feature films, animation, motion graphics, use-generated video, gameplay video recordings, web design, product design, maps, sound, and texts. We will also have access to state of the art supervisualization system at Calit2 (HIPerSpace) to explore large data sets.

Class schedule:

1 / 3.30.2011 / Introduction

Digging Into Data competition description
Patricia Cohen. In 500 Billion Words, New Window on Culture. From New York Times Humanities 2.0 series.
visual complexity

2 / 4.6.2011 / History and theory of visualization / introduction to imageJ software / "direct visualization" techniques
montage, slice, sampling

theory readings:
Manovich, Lev. What is Visualization? 2010. Visit all projects referred to in the article.

history of cartography, statistical graphics, and data visualization

1. Install ImageJ on your computer.
2. Work through imageJ basics tutorial using image(s) of your choice.
3. Read Image J documentation: Basic Concepts, Macro Language.

3 / 4.13.2011 / Digital Image processing using imageJ)
history and uses of image processing;
greyscale, saturation, hue, number of shapes measurements with imageJ built-in commands and scripts

1.Wikipedia article on Image Processing (also look at all links under "Typical Operations").
2. ImageJ Processing with ImageJ (PDF)

3 / 4.20.2011 / Digital Image processing using imageJ - continued
imageJ measurements on regions; video analysis (exporting and importing video frames; measurements with image; frame differences; shot detection)

1. Fernanda B. Viégas and Martin Wattenberg: Artistic Data Visualization. 2006. Visit the websites for all projects described in the article.
3. The N^3 Report.
2.Tara Zepel. 2008 U.S. Presidential Campaign Ads (read the blog post; the longer article is optional.)

3 / 4.27.2011 / shot detection with shotdetect; data analysis and visualization with manyeyes and Mondrian

1. Descriptive statistics.
2. Selected chapters from Computation of Style (1982). file: The_Computation_of_Style.pdf

statistical functions in Google docs
Google spreadsheets documentation

3 / 5.4.2011 / mediavis with ImagePlot; discussion of final project proposals

Each group should prepare a proposal for the final project.

Final project should present analysis and visualizations of interesting patterns in a relatively large cultural data set. You can use any data sets (still images, video, text, 3D, geo, etc.). The only requirement is that you have to analyze the actual content of the data and not only metadata.

Practically, this means that you have to use computational techniques to calculate stats and/or extract some features from your data. Of course, you can also use any metadata available and/or add metadata of your own via manual annotation.

Visualizations: you can use any software and/or write your own; the final visualizations have to be both meaningful and visually striking.

The proposal should contain the following parts (short texts):
- the data source; method for collecting the data and time estimate on how long it will take)
- research questions: what questions you want to investigate
- relevance: why this project would be interesting to others?

The proposal also need to include the small pilot study (download a small sample of your data, analyze and visualize it to see if your hypotheses hold up; if you dont get interesting results, you need to revise your idea or choose a different data set).

The proposal can be created in any format (Powerpoint, web page, blog post, etc) as long as it contains the required text parts and the visuals for the pilot study.

Note that if you dont have a solid proposal and a convincing pilot study, you would have to redo it.

Software resources:
descriptive stats online software

data exploration and visualization software:
Tableau desktop (Windows)

Examples of student projects:
The N^3 Report