The effect of caricaturing on the esthetic appeal of familiar faces, and its relation to simple proportion judgments

Abstract

It has been suggested that caricaturing enhances esthetic appeal, by making an image more strongly stimulate those areas of the brain encoding the subject's distinctive features than does the subject itself. However, some experimental work suggests that people prefer faces with proportions closer to average, or closer to a particular template. It might be that familiarity with the face is important if caricaturing is to increase the esthetic appeal of a likeness. Here we examined how automated caricaturing of photographs of nominal celebrities influenced judgments of esthetic appeal, and how familiarity with the celebrities affected these. Caricaturing monotonically decreased the esthetic appeal of the celebrity photographs, with subjects' familiarity with the celebrity not influencing this relationship. The degree to which caricaturing influenced esthetic appeal was not correlated with judgments of relative spatial dimensions for a simple shape, either in a discrimination threshold experiment or a peak-shift experiment.

Keywords: caricature; esthetics; face perception; spatial vision.

Figure 1.

Examples of caricatured (k > 1.0) and anticaricatured (k < 1.0) celebrity images used in the experiments. The difference between the celebrity's feature location and the average expected location was multiplied by the constant k, and images then morphed to have the feature at the location corresponding to this multiplied difference. The average feature locations were taken from the appropriate age- and sex-based subset of the FACES database (young female (JK), middle-aged female (AH), young male (JD), middle-aged male (HF)).

Figure 2.

Proportion that an image with a particular k was preferred in the forced-choice esthetic preference experiment. Upper panel shows the mean proportion across the 36 observers in the main experiment observing celebrity faces. Lower panel shows the mean proportion across 17 observers in the pilot experiment observing noncelebrity faces. Error bars show the 95% confidence intervals for the mean.

Figure 3.

Boxplots showing familiarity ratings for the 20 celebrity images (left panel), along with ratings for how artistic each celebrity image was as a function of k (right panel). Whiskers show the maximum and minimum values, and crosses in the right panel give mean values. Celebrity images, as ordered along the x-axis, were Audrey Hepburn (AH), Lucille Ball (LB), Elizabeth Taylor (ET), Goldie Hawn (GH), Grace Kelly (GK), Jacqueline Kennedy (JK), Marilyn Munroe (MM), Meryl Streep (MS), Sophia Loren (SL), Sigourney Weaver (SW), Dustin Hoffman (DH), Harrison Ford (HF), John Kennedy (JK), Paul Newman (PN), Richard Nixon (RN), Tom Jones (TJ), Anthony Perkins (AP), James Dean (JD), Paul McCartney (PM), and Willem Daffoe (WD).

Figure 4.

Mean matching data from the peak shift experiment (panel a), and templates generated from the average parameters of the template fits to each participant's data. Steps give linear increases in aspect ratio for the rectangular stimuli, with increasing rectangularity for higher step values. For one experimental run (filled circles), the training stimuli locations (vertical lines, lower panel) were step 7 (S+) and step 5 (S−). For the other run (unfilled squares), the rewarded (S+) and unrewarded (S−) stimuli were reversed.

Figure 5.

Each participant's random factor intercept for the linear mixed effect model for caricatured (k = 130) images, as a function of their peak shift magnitude (upper panel) or their width discrimination threshold (lower panel).

Figure 6.

Detectability of the level of caricaturing given by k. Filled circles show the mean (±SEM) of six nonnaïve participants, with the unfilled squares showing the results of a single participant naïve to the study's specific aims.