On second glance: Still no high-level pop-out effect for faces

A recent article in this journal (Hershler, O., & Hochstein, S. (2005). At first sight: A high-level pop out effect for faces. Vision Research, 45(13), 1707-1724) reported, in contradiction to several earlier studies, that photographs of human faces can be searched for efficiently (i.e., "pop out") among photographs of other objects (as long as these objects are not "too similar" to faces). An apparent search asymmetry between faces and other categories (houses, cars) pointed to the existence of a specialized "face map". Findings of impaired performance for scrambled images were presented as evidence that this face pop out is a high-level, "holistic" effect. While the main pop-out effect cannot be disputed, several choices made in that study in terms of experiment design, analysis and interpretation are questionable. After discussing these issues, I report novel experiments which show that (i) the face pop-out effect can be replicated, but under controlled conditions there is no asymmetry between faces and other objects (cars); (ii) inverting pictures and hence disrupting holistic face processing has only a minor effect on search performance; (iii) finally, search becomes inefficient when Fourier amplitude information (which carries global low-level statistical properties of images) is made irrelevant, and only phase information (carrying contour localization) can be used to detect faces. These results imply, contrary to the target article, that the face pop-out effect is mostly based on low-level factors.