Finding your Lookalike: Measuring Face Similarity Rather than Face Identity

Face images are one of the main areas of focus for computer vision, receiving on a wide variety of tasks. Although face recognition is probably the most widely researched, many other tasks such as kinship detection, facial expression classification and facial aging have been examined. In this work we propose the new, subjective task of quantifying perceived face similarity between a pair of faces. That is, we predict the perceived similarity between facial images, given that they are not of the same person. Although this task is clearly correlated with face recognition, it is different and therefore justifies a separate investigation. Humans often remark that two persons look alike, even in cases where the persons are not actually confused with one another. In addition, because face similarity is different than traditional image similarity, there are challenges in data collection and labeling, and dealing with diverging subjective opinions between human labelers. We present evidence that finding facial look-alikes and recognizing faces are two distinct tasks. We propose a new dataset for facial similarity and introduce the Lookalike network, directed towards similar face classification, which outperforms the ad hoc usage of a face recognition network directed at the same task.

1. Introduction

Have you ever seen an actor or actress and thought that they looked similar to someone that you know? Although you would clearly not confuse the two as being the same person, there might be some characteristics which may remind you of a certain person. You might be able to describe the attributes of why these people look alike, or the similarity may not even be nameable. Although your internal “face recognition algorithm” understands that these two individuals are different, something is still marking them as similar.