Michael Sheehan Morphological and population genomic evidence of selection for individual identity signaling in human faces
There's no abstract, but one area where I suspect selection of this sort may turn out to be relevant (at least more relevant than Peter Frost-style sexual selection) is in explaining European hair and eye color variation.
"Traits signaling identity should be highly variable, often display polymodal distributions, not be condition dependent (i.e., be cheap to produce and/or maintain), not be associated with fitness differences, exhibit independent assortment of component characters, and often occur as fixed phenotypes with a high degree of genetic determination."
"Is human facial distinctiveness an adaptive signal of individual identity? From a sociobiological perspective, humans seem to have the ‘perfect storm’ of selection pressures that might favor recognizability. We are extremely social, interacting repeatedly with large numbers of individuals, each with varying roles in our lives. We are extremely cooperative, and we make complex decisions about whether and how much to cooperate based on kinship, friendship and social reputation [39,78]."