Theories of object recognition have emphasized the information conveyed by shape information, whereas theories of face recognition have emphasized properties of superficial features. In the experiments reported here we used novel technology to investigate the relative contributions of shape and superficial colour information to simple categorization decisions about the sex and 'race' of faces. The results show that both shape and colour provide useful information for these decisions; shape information was particularly useful for race decisions while colour dominated sex decisions. When both sources of information were combined, the dominant source depended on viewpoint, with angled views emphasizing the contribution of shape and the full-face view colour. The results are discussed within the context of theories of face recognition and their implications for telecommunication applications are considered.