Masked perpetrators are difficult to recognize. In two experiments, we investigated ways of improving identity matching for masked perpetrators. Specifically, we evaluated the effectiveness of matching isolated facial features, namely the eyes (Experiment 1) and the mouth (Experiment 2). Participants viewed pairs of faces and determined whether they belonged to the same person or different individuals. In congruent sets, participants matched a full-face image to another full-face image or a masked image to an isolated feature. In incongruent sets, participants matched a full-face image to an image of the eyes or the mouth only or to a masked image. Matching accuracy was significantly better in congruent than incongruent sets and more so for image pairs that included isolated features. Overall, the two experiments showed that utilizing isolated facial features, such as the eyes or mouth, can be a valuable strategy for enhancing identity matching when dealing with masked perpetrators.