Can humans and automatic algorithms recognize look-alike faces?

Abstract

One of the major challenges of face recognition is to de- sign a feature extractor that reduces the intra-class vari- ations and increases the inter-class variations. The fea- ture extraction algorithm has to be robust enough to extract similar features for a particular class despite variations in quality, pose, illumination, expression, aging and disguise. The problem is exacerbated when there are two individuals with lower inter-class variations, i.e., look-alikes. In such cases, the intra-class similarity is higher than the inter- class variation for these two individuals. This research explores the problem of look-alikes faces and their effect on human performance and automatic face recognition al- gorithms. There is two fold contribution in this research: firstly, we analyze human recognition capabilities for look- alike appearances and secondly, compare it with automatic face recognition algorithms. In our analysis, we observe that neither humans nor automatic face recognition algo- rithms are efficient for the challenge of look-alikes.