Chernoff Faces

A visualisation technique introduced by Herman Chernoff in 1973 that represents multivariate data by mapping each data variable to a facial feature — eye size, eye spacing, nose length, mouth curvature, face shape, and so on — producing one cartoon face per data sample. The idea is that humans are adept at distinguishing faces, so clusters of similar samples will produce visibly similar faces. Chernoff faces have been criticised for unequal visual weighting of features and for anthropomorphic bias, and they are fundamentally inaccessible to blind users; they are included here because Bly (1982) cited them as a motivating example when proposing sonification as an alternative approach to presenting high-dimensional data.