Incongruence in Lighting Impairs Face Identification

Abstract

The effect of uniform lighting on face identity processing is little understood, despite its potential influence on our ability to recognize faces. Here, we investigated how changes in uniform lighting level affected face identification performance during face memory tests. Observers were tasked with learning a series of faces, followed by a memory test where observers judged whether the faces presented were studied before or novel. Face stimuli were presented under uniform bright or dim illuminations, and lighting across the face learning and the memory test sessions could be the same ("congruent") or different ("incongruent"). This led to four experimental conditions: (1) Bright/Dim (learning bright faces, testing on dim faces); (2) Bright/Bright; (3) Dim/Bright; and (4) Dim/Dim. Our results revealed that incongruent lighting levels across sessions (Bright/Dim and Dim/Bright) significantly reduced sensitivity (d') to faces and introduced conservative biases compared to congruent lighting levels (Bright/Bright and Dim/Dim). No significant differences in performance were detected between the congruent lighting conditions (Bright/Bright vs. Dim/Dim) and between the incongruent lighting conditions (Bright/Dim vs. Dim/Bright). Thus, incongruent lighting deteriorated performance in face identification. These findings implied that the level of uniform lighting should be considered in an illumination-specific face representation and potential applications such as eyewitness testimony.

Keywords: eyewitness testimony; face identification; face memory; face recognition; lighting; mesopic vision.

Figure 1

Example faces (top row) of the same identity under bright (left) or dim (right) lighting and their corresponding color histograms (bottom row). In actual experiments, the faces were displayed against a black background in a dark room. The rightmost plot shows the screen luminance as a function of RGB component value measured by a photometer.

Figure 2

(A) Sensitivity d’ and (B) criterion c (indicating response bias) across the four conditions. All error bars represent ±1 SEM. The asterisks (^*) in (B) represent c significantly different from zero. Conservative response biases were found in both incongruent lighting conditions (Bright/Dim & Dim/Bright).