Chernoff Faces And Glyphs


General Info

Georg Prohaska, Wolfgang Aigner, Silvia Miksch: Glyphs and Visualization of Multivariate Data, Vienna University of Technology, August 2007

Visualization and Visual Communication - a PDF slideshow about info visualisation.

Chernoff Faces


Each feature on the face represents a different variable. The overall facial impression produced by a set of variables is supposed to provide an intuitive snapshot of the data, and its meaning.

The Use of Faces to Represent Points in K-Dimensional Space Graphically

Herman Chernoff, Journal of the American Statistical Association, Vol. 68, No. 342 (Jun., 1973), pp. 361-368

original Herman Chernoff article (see library about JSTOR access (thru city))

A novel method of representing multivariate data is presented. Each point in k-dimensional space, k ≤ 18, is represented by a cartoon of a face whose features, such as length of nose and curvature of mouth, correspond to components of the point. Thus every multivariate observation is visualized as a computer-drawn face. This presentation makes it easy for the human mind to grasp many of the essential regularities and irregularities present in the data. Other graphical representations are described briefly.

A Critique of Chernoff Faces

A very interesting article by Robert Kosara, 2007-02-25


Other Glyph Systems

The Which Blair Project


The Which Blair Project: A Quick Visual Method for Evaluating Perceptual Color Maps, Bernice E. Rogowitz and Alan D. Kalvin, Visual Analysis Group, IBM T.J. Watson Research Center, Hawthorne, NY

We have developed a fast, perceptual method for selecting color scales for data visualization that takes advantage of our sensitivity to luminance variations in human faces. To do so, we conducted experiments in which we mapped various color scales onto the intensitiy values of a digitized photograph of a face and asked observers to rate each image. We found a very strong correlation between the perceived naturalness of the images and the degree to which the underlying color scales increased monotonically in luminance. Color scales that did not include a monotonicallyincreasing luminance component produced no positive rating scores. Since color scales with monotonic luminance profiles are widely recommended for visualizing continuous scalar data, a purely visual technique for identifying such color scales could be very useful, especially in situations where color calibration is not integrated into the visualization environment, such as over the Internet.



Werner Horn et al: VIE-VISU: Metaphor Graphics to Visualize ICU Data over Time

The aim of the project was to develop a visualization system which support the easy recognition of a patient's status and its change over time. VIE-VISU visualizes data stored periodically (or continuously) in a patient data management system (PDMS) of an intensive care unit (ICU).

An Experimental Analysis of the Effectiveness of Features in Chernoff Faces
Christopher J. Morris, David S. Ebert, Penny Rheingans, University of Maryland, Baltimore County, 1999

"Chernoff face feature perception is a serial process and is not pre-attentive"
"eye size and eyebrow slant produced the most accurate results"

Chernoff Faces are supposed to work well because they use our "preattentive" capabilities - i.e. we shouldn't have to think about them, but should have an instant, intuitive reaction to the represented data. These authors' research suggests that this is not so.

full paper

The Empathic Visualisation Algorithm: Chernoff Faces Revisited
Andreas Loizides & Mel Slater, UCL


(can't find a date, but looks like current research)

Loizides's research page can be found here. This research looks very relevant to what I am doing as it involves financial data and doesn't simply map each variable randomly to a facial feature but interprets the data in terms of human emotions and builds 3D heads based on this.

Paper: Escaping Flatland: Chernoff's Faces Revisited
Wendy B. Dickinson
Proceedings of the Twenty-Sixth Annual SAS® Users Group International Conference
Cary, NC: SAS Institute Inc., 2001.

Tufte (1990) asked, "How are we to represent the rich visual world of experience and measurement on mere Flatland?" This study used criteria of elegance, simplicity,and clarity to determine the most compelling images produced with SAS 6.12 algorithmic analysis.
Escaping from Flatland requires innovative methods and unique problem resolution. This study investigated and provided possible solutions for "escaping Flatland."

Add a New Comment
Unless otherwise stated, the content of this page is licensed under Creative Commons Attribution-ShareAlike 3.0 License